nrimsky / CAALinks
Steering Llama 2 with Contrastive Activation Addition
☆188Updated last year
Alternatives and similar repositories for CAA
Users that are interested in CAA are comparing it to the libraries listed below
Sorting:
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆98Updated 2 years ago
- [ICLR 2025] General-purpose activation steering library☆111Updated last month
- ☆179Updated 11 months ago
- ☆234Updated last year
- ☆190Updated last week
- Steering vectors for transformer language models in Pytorch / Huggingface☆125Updated 8 months ago
- Using sparse coding to find distributed representations used by neural networks.☆279Updated last year
- A library for efficient patching and automatic circuit discovery.☆78Updated 3 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆181Updated 6 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆218Updated last week
- Algebraic value editing in pretrained language models☆66Updated last year
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆290Updated 4 months ago
- ☆247Updated last year
- Sparse probing paper full code.☆62Updated last year
- ☆131Updated this week
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆136Updated 3 months ago
- ☆92Updated last year
- ☆126Updated last year
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆157Updated this week
- A resource repository for representation engineering in large language models☆138Updated 11 months ago
- ☆57Updated 2 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆66Updated 10 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆56Updated last year
- ☆98Updated last year
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆82Updated 7 months ago
- Improving Alignment and Robustness with Circuit Breakers☆238Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 11 months ago
- Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization☆32Updated last year
- AI Logging for Interpretability and Explainability🔬☆129Updated last year
- Code for In-context Vectors: Making In Context Learning More Effective and Controllable Through Latent Space Steering☆190Updated 8 months ago