mech-interp 5
- How does audio language model hold speaker identity throughout an utterance.
- How does refusal ablation work?
- Noobs guide to mechanistic interpretability
- Removing the Refusal Direction:How I Turned Param-1 Into an Uncensored Model Without Fine-Tuning
- Executing Toxicity Mechanistic Localization of Toxic Behavior in a Fine-Tuned Transformer