sae-feature-activation-state
zjunlp/MechanistUse this skill when working with Sparse Autoencoders (SAEs) for feature analysis, particularly for studying feature splitting, absorption, and attribution in…
Scores out of 100 · grade A
2026-08-18Works
40% of the score100/100
- Loads cleanly: valid frontmatter, required fields present, no dangling references.
Maintained
25% of the score100/100
- no commits in the last 12 weeks
Adopted
20% of the score22/100
- 42 stars on the source repo.
Documented
15% of the score100/100
- 3,159 words with worked examples.
- Ships 4 bundled files.
Install
npx skills add zjunlp/Mechanist/sae-feature-activation-stateWhat it says it does
Use this skill when working with Sparse Autoencoders (SAEs) for feature analysis, particularly for studying feature splitting, absorption, and attribution in language models. Activate for tasks involving SAE feature ablation, probing experiments, or analyzing how SAE latents affect model outputs in spelling and token-level tasks.
Also in zjunlp/Mechanist
| Artifact | Score | What the check found | Type | Reach | Last commit |
|---|---|---|---|---|---|
| dynamic-componentszjunlp/Mechanist | clean | Skill | 42 stars | today | |
| layer-wise-representationzjunlp/Mechanist | clean | Skill | 42 stars | today | |
| static-parameterszjunlp/Mechanist | clean | Skill | 42 stars | today | |
| representation-engineeringzjunlp/Mechanist | clean | Skill | 42 stars | today | |
| steering-vectorszjunlp/Mechanist | clean | Skill | 42 stars | today | |
| neuron-value-weightzjunlp/Mechanist | clean | Skill | 42 stars | today |
Other general skills
Browse all| Artifact | Score | What the check found | Category | Reach | Last commit |
|---|---|---|---|---|---|
| brainstormingobra/superpowers | clean | General | 334,894 installs | 2 days ago | |
| codebase-designmattpocock/skills | clean | General | 452,437 installs | today | |
| dispatching-parallel-agentsobra/superpowers | clean | General | 170,666 installs | 2 days ago | |
| verification-before-completionobra/superpowers | clean | General | 185,676 installs | 2 days ago | |
| create-cowork-pluginanthropics/knowledge-work-plugins | clean | General | 2,443 installs | today | |
| explore-dataanthropics/knowledge-work-plugins | clean | General | 5,170 installs | today |
Put this measurement in your README
A badge carrying how many listings this index holds from the repository and how many pass every static structural check. It reads from this index every time somebody loads your page, so it changes when the measurement changes and there is nothing to keep up to date. Free, no account, and the value is not something you or we can set by hand.
[](https://skillworks.kynth.studio/?q=zjunlp%2FMechanist)Would rather not hotlink us? Every badge is also served in shields.io’s endpoint schema, so shields renders the image and your readers never talk to our domain:
Published by Toolproof, the masthead over this index and eight others. The method behind the number is at toolproof.kynth.studio/methodology, and the whole thing is readable as JSON with no key at /api.
