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.
☆145Updated 5 months ago
Alternatives and similar repositories for LogitLens4LLMs
Users that are interested in LogitLens4LLMs are comparing it to the libraries listed below
Sorting:
- A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..☆290Updated 3 weeks ago
- code for EMNLP 2024 paper: Neuron-Level Knowledge Attribution in Large Language Models☆48Updated last year
- 📜 Paper list on decoding methods for LLMs and LVLMs☆66Updated 2 months ago
- [ICLR 2025] Code and Data Repo for Paper "Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation"☆93Updated last year
- [NeurIPS 2024] How do Large Language Models Handle Multilingualism?☆50Updated last year
- [EMNLP 2024] The official GitHub repo for the survey paper "Knowledge Conflicts for LLMs: A Survey"☆150Updated last year
- awesome SAE papers☆70Updated 7 months ago
- Implementation code for ACL2024：Advancing Parameter Efficiency in Fine-tuning via Representation Editing☆14Updated last year
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)☆127Updated last year
- ☆72Updated 9 months ago
- Awesome-Long2short-on-LRMs is a collection of state-of-the-art, novel, exciting long2short methods on large reasoning models. It contains…☆256Updated 5 months ago
- The repo for In-context Autoencoder☆162Updated last year
- ☆180Updated last year
- A Survey on Data Selection for Language Models☆254Updated 8 months ago
- Chain of Thoughts (CoT) is so hot! so long! We need short reasoning process!☆72Updated 9 months ago
- FeatureAlignment = Alignment + Mechanistic Interpretability☆34Updated 10 months ago
- This repository contains a regularly updated paper list for LLMs-reasoning-in-latent-space.☆261Updated last week
- Official Code Repository for LM-Steer Paper: "Word Embeddings Are Steers for Language Models" (ACL 2024 Outstanding Paper Award)☆134Updated 6 months ago
- Model merging is a highly efficient approach for long-to-short reasoning.☆96Updated 3 months ago
- The Paper List on Data Contamination for Large Language Models Evaluation.☆108Updated 2 months ago
- A curated list of resources for activation engineering☆121Updated 3 months ago
- RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024☆87Updated last year
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆68Updated last year
- ☆39Updated last year
- LLM Unlearning☆178Updated 2 years ago
- Repository for Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learning☆168Updated last year
- [EMNLP 2023] MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questions☆118Updated last year
- ☆90Updated last year
- [NeurIPS 2025] Implementation for the paper "The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning"☆150Updated 2 months ago
- [NeurIPS 2024] The official implementation of paper: Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs.☆134Updated 9 months ago