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.
β99Updated last week
Alternatives and similar repositories for LogitLens4LLMs
Users that are interested in LogitLens4LLMs are comparing it to the libraries listed below
Sorting:
- π Paper list on decoding methods for LLMs and LVLMsβ55Updated last month
- A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..β265Updated 5 months ago
- code for EMNLP 2024 paper: Neuron-Level Knowledge Attribution in Large Language Modelsβ41Updated 9 months ago
- [ICLR 2025] Code and Data Repo for Paper "Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation"β75Updated 8 months ago
- Code associated with Tuning Language Models by Proxy (Liu et al., 2024)β114Updated last year
- This repository contains a regularly updated paper list for LLMs-reasoning-in-latent-space.β153Updated last week
- FeatureAlignment = Alignment + Mechanistic Interpretabilityβ29Updated 5 months ago
- β66Updated 4 months ago
- awesome SAE papersβ42Updated 3 months ago
- Implementation code for ACL2024οΌAdvancing Parameter Efficiency in Fine-tuning via Representation Editingβ14Updated last year
- [NeurIPS 2024] How do Large Language Models Handle Multilingualism?β38Updated 9 months ago
- Model merging is a highly efficient approach for long-to-short reasoning.β80Updated 2 months ago
- β81Updated 8 months ago
- The Paper List on Data Contamination for Large Language Models Evaluation.β99Updated last week
- Awesome-Long2short-on-LRMs is a collection of state-of-the-art, novel, exciting long2short methods on large reasoning models. It containsβ¦β244Updated 2 weeks ago
- β33Updated 2 months ago
- RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024β78Updated 10 months ago
- A Survey on Data Selection for Language Modelsβ247Updated 3 months ago
- The repo for In-context Autoencoderβ135Updated last year
- Implementation for the paper "The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning"β91Updated last month
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineeringβ63Updated 9 months ago
- LoFiT: Localized Fine-tuning on LLM Representationsβ40Updated 7 months ago
- Repository for Label Words are Anchors: An Information Flow Perspective for Understanding In-Context Learningβ163Updated last year
- Chain of Thoughts (CoT) is so hot! so long! We need short reasoning process!β69Updated 4 months ago
- Official repository for ACL 2025 paper "ProcessBench: Identifying Process Errors in Mathematical Reasoning"β170Updated 3 months ago
- [EMNLP 2023] MQuAKE: Assessing Knowledge Editing in Language Models via Multi-Hop Questionsβ114Updated 11 months ago
- TokenSkip: Controllable Chain-of-Thought Compression in LLMsβ173Updated last month
- [EMNLP 2024] The official GitHub repo for the survey paper "Knowledge Conflicts for LLMs: A Survey"β133Updated 11 months ago
- A curated list of resources for activation engineeringβ100Updated 2 months ago
- [EMNLP 2024] Source code for the paper "Learning Planning-based Reasoning with Trajectory Collection and Process Rewards Synthesizing".β80Updated 7 months ago