跳到正文
cccskills

“sae”的搜索结果

40 个 · 按相关度排序

saelens

免费有简介AI 评分 80分

使用稀疏自编码器将语言模型内部的激活分解为少量特征,研究模型学到的概念。涵盖预训练SAE分析、自定义训练、重建质量评估,以及利用特征调整输出的实验。

  • 使用预训练SAE研究特征
  • 针对特定模型层训练SAE
  • 比较不同输入文本的特征响应
NousResearch/hermes-agent25.5万2026年10月19日 更新

Use SAELens to train and analyze sparse autoencoders, which separate neural network activity into features that may represent recognizable concepts. Explore pretrained features, evaluate reconstruction quality, and investigate how individual features influence language model outputs.

中文简介正在准备中。当前显示英语简介。

  • Exploring features with a pretrained SAE
  • Training and evaluating a custom SAE
  • Studying overlapping concepts in model activity
davila7/claude-code-templates3.3万2026年10月20日 更新

Use SAELens to train and analyze sparse autoencoders, which break model activations into a small set of interpretable features. Explore pretrained features, evaluate reconstruction quality, troubleshoot training, and test how individual features influence generated text.

中文简介正在准备中。当前显示英语简介。

  • Exploring features in a pretrained SAE
  • Training an SAE for a selected model layer
  • Investigating inactive features and reconstruction errors
Orchestra-Research/AI-Research-SKILLs1.4万2026年10月11日 更新

Assess WPA3 wireless security by reviewing mixed WPA2/WPA3 settings and SAE, its password authentication method. Examine implementation weaknesses, H2E support, and 6 GHz requirements to determine relevant tests and detection signals.

中文简介正在准备中。当前显示英语简介。

  • Reviewing security settings on WPA3 wireless networks
  • Assessing downgrade risks in mixed WPA2/WPA3 deployments
  • Organizing SAE implementation and H2E checks
SnailSploit/Claude-Red76212026年10月13日 更新

Plan tiered administration for Active Directory by separating administrative accounts and systems into three levels. Cover dedicated administration workstations, authentication restrictions, and verification checks to help limit credential theft and the spread of compromise.

中文简介正在准备中。当前显示英语简介。

  • Designing tiered Active Directory administration
  • Separating privileged accounts by administrative tier
  • Planning dedicated administration workstations
mukul975/Anthropic-Cybersecurity-Skills3.5万2026年8月31日 更新

saelens

免费

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

中文简介正在准备中。当前显示原文说明。

huang-sh/DeepScience42026年7月15日 更新

WPA3 / SAE (Simultaneous Authentication of Equals) attack methodology — transition-mode (mixed WPA2/WPA3) downgrade, Dragonblood side-channel attacks (CVE-2019-9494, 9495, 13377, 13456), SAE auth flooding for AP CPU exhaustion, Hash-to-Element (H2E) timing analysis, group downgrade, and 6 GHz / Wi-Fi 6E spec implications (PMF mandatory, no transition mode allowed). Use when target advertises WPA3-SAE or WPA3-Personal/Enterprise, or operates in 6 GHz where WPA3 + PMF are required by spec.

中文简介正在准备中。当前显示原文说明。

ajtazer/heckit22026年10月7日 更新

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

中文简介正在准备中。当前显示原文说明。

foryourhealth111-pixel/Vibe-Skills37292026年10月20日 更新

Fornece orientação para treinar e analisar Autoencodificadores Esparsos (SAEs) usando SAELens para decompor ativações de redes neurais em features interpretáveis. Use ao descobrir features interpretáveis, analisar superposição ou estudar representações monossemânticas em modelos de linguagem.

中文简介正在准备中。当前显示原文说明。

artubss/SKILLS-CLAUDE-CODE112026年5月17日 更新

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

中文简介正在准备中。当前显示原文说明。

Lord1Egypt/awesome-skill-forge22026年6月10日 更新

ipsae

免费

Binder design ranking using ipSAE (interprotein Score from Aligned Errors). Use this skill when: (1) Ranking binder designs for experimental testing, (2) Filtering BindCraft or RFdiffusion outputs, (3) Comparing AF2/AF3/Boltz predictions, (4) Predicting binding success rates, (5) Need better ranking than ipTM or iPAE. For structure prediction, use chai or alphafold. For QC thresholds, use protein-qc.

中文简介正在准备中。当前显示原文说明。

BioTender-max/awesome-bio-agent-skills2032026年7月2日 更新

Conduct temperament-based health assessment from Hildegard von Bingen's Causae et Curae. Evaluates the four temperaments (sanguine, choleric, melancholic, phlegmatic), elemental correspondences (air, fire, earth, water), and provides dietary and lifestyle recommendations for rebalancing. Use when understanding constitutional type in Hildegardian terms, experiencing imbalance (fatigue, digestive issues, mental fog) needing holistic guidance, seeking dietary recommendations by temperament, or researching medieval humoral medicine.

中文简介正在准备中。当前显示原文说明。

pjt222/agent-almanac422026年10月15日 更新

Use when a task needs the judgment of an Automotive Engineering Technician — setting up and instrumenting test equipment (strain-gauge bridges, thermocouples, load/torque sensors) to an engineer's written test plan, selecting DAQ sample rate and an SAE J211 CFC filter class for a vehicle test channel, verifying instrument calibration (torque wrench, thermocouple, load cell, shunt-cal check on a strain bridge) against a traceable standard before a test run, reducing dyno or road-load test data (SAE J1349 power correction, rainflow-counted durability damage fraction) into engineering units, and documenting test results against the engineer's target with stated margin. Distinct from an automotive engineer (owns the system-level design decisions — structure, powertrain sizing, suspension geometry, NVH) — this role installs the sensors, configures the DAQ, executes the instrumented test, and reduces the data under a design and test plan the engineer specified.

中文简介正在准备中。当前显示原文说明。

wonsukchoi/domain-experts222026年10月19日 更新

Implement Microsoft's Enhanced Security Admin Environment (ESAE) tiered administration model for Active Directory. Covers Tier 0/1/2 separation, privileged access workstations (PAWs), administrative f

中文简介正在准备中。当前显示原文说明。

andycungkrinx91/konoha92026年10月19日 更新

Synthesized reference notes from three US Government vehicle-safety sources: NHTSA Cybersecurity Best Practices for the Safety of Modern Vehicles (updated 2022, final), NHTSA Automated Driving Systems 2.0: A Vision for Safety (2017), and a 16-section selection of 49 CFR Part 571 (FMVSS) pinned at eCFR versioner date 2025-01-01. Use for voluntary vehicle cybersecurity practices, the ADS 2.0 twelve priority safety design elements, and FMVSS occupant protection, brakes/stability/lighting, and fuel/EV integrity requirements. Not ISO 26262, not ASPICE, not ISO/SAE 21434, not UNECE R155/R156, not SAE J3016, and not the full Part 571; the FMVSS material is a selection of vehicle-level minimum performance standards, not a process standard.

中文简介正在准备中。当前显示原文说明。

jgsystemsconsulting/jgs-se-knowledge-packs82026年10月15日 更新

Signpost (not a knowledge pack) for the functional safety standards landscape: IEC 61508, ISO 26262, ISO/SAE 21434, UL 4600, SAE J3016, and ASPICE. Contains NO source content: designation, edition, owner, status, and an official catalogue URL only. Use when you need to identify or locate a functional safety standard. All six are paywalled or carry no redistribution grant and cannot be packaged; open paths point at US Government packs, which are not equivalents.

中文简介正在准备中。当前显示原文说明。

jgsystemsconsulting/jgs-se-knowledge-packs82026年10月15日 更新

Implement Microsoft's Enhanced Security Admin Environment (ESAE) tiered administration model for Active Directory. Covers Tier 0/1/2 separation, privileged access workstations (PAWs), administrative f

中文简介正在准备中。当前显示原文说明。

micsapp/micstec-skills42026年3月20日 更新

Provides guidance for training and analyzing Sparse Autoencoders (SAEs) using SAELens to decompose neural network activations into interpretable features. Use when discovering interpretable features, analyzing superposition, or studying monosemantic representations in language models.

中文简介正在准备中。当前显示原文说明。

ibragimov-oasis/vibe-coder32026年6月24日 更新

Implement Microsoft's Enhanced Security Admin Environment (ESAE) tiered administration model for Active Directory. Covers Tier 0/1/2 separation, privileged access workstations (PAWs), administrative f

中文简介正在准备中。当前显示原文说明。

aniket2348823/Vul-Agent22026年6月9日 更新

Plan and carry out wireless security assessments, from surveying nearby networks to checking authentication weaknesses and recording findings. Covers personal and enterprise Wi-Fi, rogue access points, and testing considerations for Wi-Fi 6, 6E, and 7.

中文简介正在准备中。当前显示英语简介。

  • Planning a corporate Wi-Fi security assessment
  • Reviewing WPA2 and WPA3 authentication weaknesses
  • Testing enterprise Wi-Fi against rogue access points
SnailSploit/Claude-Red76212026年10月13日 更新

esmfold2

免费

Predict structures of protein, nucleic acid, and small-molecule complexes with ESMFold2, using single sequences or aligned related sequences. The skill also covers ESMC models for numerical sequence representations, mutation scoring, and predictions of contacts between residues.

中文简介正在准备中。当前显示英语简介。

  • Predicting complex structures from single sequences
  • Assessing designed binders with ESMFold2-Fast
  • Predicting structures using aligned related sequences
aipoch/open-science52922026年10月20日 更新

Write comprehensive clinical reports including case reports (CARE guidelines), diagnostic reports (radiology/pathology/lab), clinical trial reports (ICH-E3, SAE, CSR), and patient documentation (SOAP, H&P, discharge summaries). Full support with templates, regulatory compliance (HIPAA, FDA, ICH-GCP), and validation tools.

中文简介正在准备中。当前显示原文说明。

foryourhealth111-pixel/Vibe-Skills37292026年10月20日 更新

Prüft, ob AGB-Änderungen durch ausdrückliche Zustimmung, Schweigen oder Weiternutzung wirksam vereinbart werden können. Für Änderungsmitteilungen einschließlich Bankbedingungen; liefert Zustimmungsweg, Beweisplan und konkrete Fassung.

中文简介正在准备中。当前显示原文说明。

Klotzkette/claude-fuer-deutsches-recht17242026年10月19日 更新

Für Leistungsänderung Produktupdate: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt.

中文简介正在准备中。当前显示原文说明。

Klotzkette/claude-fuer-deutsches-recht17242026年10月19日 更新