logix-project / logixLinks
AI Logging for Interpretability and Explainability🔬
☆125Updated last year
Alternatives and similar repositories for logix
Users that are interested in logix are comparing it to the libraries listed below
Sorting:
- ☆96Updated last year
- [ICLR 2025] General-purpose activation steering library☆94Updated 3 weeks ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆76Updated 5 months ago
- DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models (ICLR 2024)☆74Updated 10 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆124Updated 2 months ago
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆110Updated 6 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆176Updated 4 months ago
- ☆50Updated 3 months ago
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆78Updated last year
- LoFiT: Localized Fine-tuning on LLM Representations☆40Updated 7 months ago
- Steering Llama 2 with Contrastive Activation Addition☆174Updated last year
- [NeurIPS'23] Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors☆79Updated 8 months ago
- ☆47Updated last year
- ☆223Updated last year
- ☆24Updated 6 months ago
- A Survey on Data Selection for Language Models☆247Updated 3 months ago
- Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the p…☆12Updated 6 months ago
- ☆44Updated last year
- The Paper List on Data Contamination for Large Language Models Evaluation.☆99Updated this week
- ☆53Updated 2 years ago
- Data and code for the preprint "In-Context Learning with Long-Context Models: An In-Depth Exploration"☆39Updated last year
- A library for efficient patching and automatic circuit discovery.☆76Updated last month
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆63Updated 8 months ago
- ☆162Updated 9 months ago
- `dattri` is a PyTorch library for developing, benchmarking, and deploying efficient data attribution algorithms.☆84Updated 2 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆96Updated last year
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆114Updated last year
- ☆60Updated 5 months ago
- ☆50Updated last year
- ☆39Updated last year