⚓️ Repository for the "Thought Anchors: Which LLM Reasoning Steps Matter?" paper.
☆143Oct 27, 2025Updated 10 months ago
Alternatives and similar repositories for thought-anchors
Users that are interested in thought-anchors are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ⚓️ Interactive playground for the "Thought Anchors: Which LLM Reasoning Steps Matter?" paper.☆18Dec 20, 2025Updated 9 months ago
- This was designed for interp researchers who want to do research on or with interp agents to give quality of life improvements and fix …☆146Feb 8, 2026Updated 7 months ago
- Code repo for the model organisms and convergent directions of EM papers.☆86Sep 22, 2025Updated last year
- ☆40Jul 9, 2025Updated last year
- ☆64Jul 4, 2025Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆87Feb 18, 2026Updated 7 months ago
- Repository for the "Chain-of-Thought Reasoning In The Wild Is Not Always Faithful" paper☆35Mar 31, 2026Updated 5 months ago
- ☆24Updated this week
- ☆16Nov 14, 2025Updated 10 months ago
- Unified access to Large Language Model modules using NNsight☆120Updated this week
- Global CoT Analysis: Initial attempts to uncover patterns across many chains of thought☆20Feb 10, 2026Updated 7 months ago
- Code for Negation Neglect☆18May 22, 2026Updated 4 months ago
- Course Materials for Interpretability of Large Language Models (0368.4264) at Tel Aviv University☆339Feb 8, 2026Updated 7 months ago
- Code repository for "Eliciting Secret Knowledge from Language Models"☆24Mar 30, 2026Updated 5 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆20Mar 16, 2026Updated 6 months ago
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆1,108Updated this week
- Tools for exploring Transformer neuron behaviour, including input pruning and diversification.☆11Jun 6, 2023Updated 3 years ago
- Training LLMs to Report Their Learned Behaviors☆29Apr 28, 2026Updated 4 months ago
- ☆25Jul 8, 2026Updated 2 months ago
- ☆16Oct 13, 2025Updated 11 months ago
- ✱ Understanding the underlying learning dynamics of simple tasks in Transformer networks☆19Aug 16, 2024Updated 2 years ago
- Parameter Decomposition☆143Sep 15, 2026Updated last week
- ☆24Aug 30, 2025Updated last year
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- ADAG: Transluce's MLP neuron-level circuit tracing library☆39Apr 10, 2026Updated 5 months ago
- ☆28Feb 20, 2026Updated 7 months ago
- ☆115Sep 16, 2026Updated last week
- ☆18Jul 9, 2025Updated last year
- A library for mechanistic interpretability of GPT-style language models☆3,900Updated this week
- Agent observability and replay tooling for AI safety & interpretability research.☆116Jun 19, 2026Updated 3 months ago
- A python sdk for LLM finetuning and inference on runpod infrastructure☆30Sep 7, 2026Updated 2 weeks ago
- ☆25Mar 30, 2026Updated 5 months ago
- ☆1,318Updated this week
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Official codebase for "Analyzing the Generalization and Reliability of Steering Vectors"☆23Dec 14, 2024Updated last year
- ☆21Apr 26, 2026Updated 4 months ago
- ☆102Apr 18, 2026Updated 5 months ago
- Applies ROME and MEMIT on Mamba-S4 models☆16Apr 5, 2024Updated 2 years ago
- Code and data for the paper "LatentLens: Revealing Highly Interpretable Visual Tokens in LLMs"☆50Mar 31, 2026Updated 5 months ago
- A library for efficient patching and automatic circuit discovery.☆103Aug 17, 2026Updated last month
- Mechanistic Interpretability Visualizations using React☆366Apr 30, 2026Updated 4 months ago