Popular repositories Loading

1. transcoder_circuits transcoder_circuits Public

   Jupyter Notebook 178 29

2. llm-steering-opt llm-steering-opt Public

   Tools for optimizing steering vectors in LLMs.

   Jupyter Notebook 13 3

3. one-shot-steering-misalignment one-shot-steering-misalignment Public

   Code and results on finding one-shot steering vectors that mediate emergent misalignment

   Jupyter Notebook 10 3

4. one-shot-steering-repro one-shot-steering-repro Public

   Code for reproducing the results from our paper "Investigating Generalization of One-shot LLM Steering Vectors"

   Jupyter Notebook 4 1

5. ObservablePropagation ObservablePropagation Public

   Code for our paper on observable propagation

   Jupyter Notebook 3 1

6. multilayer-transcoder-reversing multilayer-transcoder-reversing Public

   Reverse-engineering transcoder features in multi-layer LLMs

   Jupyter Notebook 2