nrimsky / CAALinks
Steering Llama 2 with Contrastive Activation Addition
☆174Updated 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☆96Updated last year
- [ICLR 2025] General-purpose activation steering library☆94Updated 3 weeks ago
- ☆162Updated 9 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆122Updated 6 months ago
- Algebraic value editing in pretrained language models☆65Updated last year
- ☆184Updated last month
- Using sparse coding to find distributed representations used by neural networks.☆262Updated last year
- ☆223Updated last year
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆143Updated last week
- A library for efficient patching and automatic circuit discovery.☆76Updated last month
- ☆111Updated last month
- Function Vectors in Large Language Models (ICLR 2024)☆176Updated 4 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆206Updated this week
- Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization☆30Updated last year
- ☆90Updated last year
- ☆237Updated 10 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆76Updated 5 months ago
- Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".☆257Updated 2 months ago
- ☆47Updated last month
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆124Updated last month
- A resource repository for representation engineering in large language models☆130Updated 9 months ago
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆63Updated 8 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆58Updated 9 months ago
- Sparse probing paper full code.☆59Updated last year
- ☆96Updated last year
- Improving Alignment and Robustness with Circuit Breakers☆226Updated 11 months ago
- ☆47Updated last year
- AI Logging for Interpretability and Explainability🔬☆125Updated last year
- ☆122Updated last year
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆110Updated 6 months ago