Skip to content
/ interp-refusal-tokens Public

We study whether categorical refusal tokens enable controllable and interpretable safety behavior in language models.

License

Apache-2.0 license
7 stars 1 fork Branches Tags Activity
Star
Notifications You must be signed in to change notification settings

RishabSA/interp-refusal-tokens

BranchesTags

Repository files navigation

From Refusal Tokens to Refusal Control: Discovering and Steering Category-Specific Refusal Directions

About

We study whether categorical refusal tokens enable controllable and interpretable safety behavior in language models.

Topics

machine-learning research ai deep-learning pytorch artificial-intelligence safety llama steering neurips llm mechanistic-interpretability llm-safety refusal llama3 transformer-lens llm-refusal

Resources

Readme

License

Apache-2.0 license
Activity

Stars

7 stars

Watchers

0 watching

Forks

1 fork
Report repository

Releases

No releases published

Packages

No packages published

Contributors 2

  •  
  •  

Languages