Pinned Loading

1. reasoning-lora-interp reasoning-lora-interp Public

   This repository contains the code for the paper "Rank-1 Reasoning: Minimal Parameter Diffs Encode Interpretable Reasoning Signals"

   Python 2

2. persona-interface persona-interface Public

   Python

3. sae-kit sae-kit Public

   A library for optimizing SAE encodings

   Python

4. scale-dependent-elicitation scale-dependent-elicitation Public

   This repository contains code for the paper "Scale-Dependent Elicitation of Reasoning in LLMs".

   Python

5. monosemanticity-repro monosemanticity-repro Public

   Open source repro of "Towards Monosemanticity"

   Jupyter Notebook 33 2