EleutherAI / steering-llama3Links
☆30Updated last year
Alternatives and similar repositories for steering-llama3
Users that are interested in steering-llama3 are comparing it to the libraries listed below
Sorting:
- Steering vectors for transformer language models in Pytorch / Huggingface☆124Updated 7 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆211Updated last week
- Sparse Autoencoder Training Library☆54Updated 4 months ago
- ☆34Updated last year
- ☆127Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆220Updated 9 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28Updated last year
- A library for efficient patching and automatic circuit discovery.☆76Updated 2 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 11 months ago
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆19Updated 11 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆80Updated 10 months ago
- ☆54Updated 10 months ago
- ☆242Updated 11 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆202Updated 10 months ago
- ☆71Updated 3 weeks ago
- ☆106Updated 7 months ago
- Steering Llama 2 with Contrastive Activation Addition☆180Updated last year
- Applying SAEs for fine-grained control☆23Updated 9 months ago
- ☆29Updated last year
- A library for mechanistic anomaly detection☆22Updated 8 months ago
- Modified to support crosscoder training.☆23Updated last month
- ☆186Updated 2 months ago
- Mechanistic Interpretability Visualizations using React☆289Updated 9 months ago
- ☆76Updated 4 months ago
- Attribution-based Parameter Decomposition☆30Updated 3 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆24Updated 10 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- ☆124Updated last week
- ☆171Updated 10 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆72Updated last year