Popular repositories Loading

1. refusal_direction refusal_direction Public

   Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".

   Python 139 28

2. andyrdt.github.io andyrdt.github.io Public

   SCSS 1

3. CircuitsVis CircuitsVis Public

   Forked from TransformerLensOrg/CircuitsVis

   Mechanistic Interpretability Visualizations using React

   Jupyter Notebook

4. mi mi Public

   Repo to track miscellaneous mi stuff

   Jupyter Notebook 3

5. llm-attacks llm-attacks Public

   Forked from llm-attacks/llm-attacks

   Python

6. SycophancySteering SycophancySteering Public

   Forked from nrimsky/CAA

   Modulating sycophancy in llama-2 via activation steering

   Python