zhenyu-02 / LogitLens4LLMsLinks
A versatile toolkit for applying Logit Lens to modern large language models (LLMs). Currently supports Llama-3.1-8B and Qwen-2.5-7B, enabling layer-wise analysis of hidden states and predictions.
☆132Updated 3 months ago
Alternatives and similar repositories for LogitLens4LLMs
Users that are interested in LogitLens4LLMs are comparing it to the libraries listed below
Sorting:
- code for EMNLP 2024 paper: Neuron-Level Knowledge Attribution in Large Language Models☆48Updated last year
- A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..☆286Updated 8 months ago
- 📜 Paper list on decoding methods for LLMs and LVLMs☆66Updated last month
- Awesome-Long2short-on-LRMs is a collection of state-of-the-art, novel, exciting long2short methods on large reasoning models. It contains…☆255Updated 3 months ago
- [ICLR 2025] Code and Data Repo for Paper "Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation"☆88Updated 11 months ago
- ☆68Updated 7 months ago
- FeatureAlignment = Alignment + Mechanistic Interpretability☆33Updated 9 months ago
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆123Updated last year
- The official GitHub repository of the paper "Recent advances in large langauge model benchmarks against data contamination: From static t…☆47Updated 2 months ago
- A Survey on Data Selection for Language Models☆252Updated 7 months ago
- Implementation code for ACL2024：Advancing Parameter Efficiency in Fine-tuning via Representation Editing☆14Updated last year
- awesome SAE papers☆63Updated 6 months ago
- [NeurIPS 2024] How do Large Language Models Handle Multilingualism?☆46Updated last year
- This repository contains a regularly updated paper list for LLMs-reasoning-in-latent-space.☆215Updated this week
- Model merging is a highly efficient approach for long-to-short reasoning.☆92Updated last month
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆67Updated last year
- A curated list of resources for activation engineering☆114Updated 2 months ago
- [EMNLP 2024] The official GitHub repo for the survey paper "Knowledge Conflicts for LLMs: A Survey"☆149Updated last year
- ☆66Updated 9 months ago
- A simple toolkit for benchmarking LLMs on mathematical reasoning tasks. 🧮✨☆271Updated last year
- Repository for Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning☆167Updated last year
- [NeurIPS 2025] Implementation for the paper "The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning"☆127Updated last month
- This is the official GitHub repository for our survey paper "Beyond Single-Turn: A Survey on Multi-Turn Interactions with Large Language …☆146Updated 6 months ago
- ☆174Updated last year
- This is the repository of DEER, a Dynamic Early Exit in Reasoning method for Large Reasoning Language Models.☆177Updated 5 months ago
- [EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆193Updated last week
- The Paper List on Data Contamination for Large Language Models Evaluation.☆107Updated 3 weeks ago
- Chain of Thoughts (CoT) is so hot! so long! We need short reasoning process!☆70Updated 8 months ago
- ☆89Updated 11 months ago
- LLM Unlearning☆177Updated 2 years ago