A collection of lightweight interpretability scripts to understand how LLMs think
☆92Mar 18, 2026Updated 7 months ago
Alternatives and similar repositories for llm-interp
Users that are interested in llm-interp are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- H-Net Dynamic Hierarchical Architecture☆81Sep 11, 2025Updated last year
- Official PyTorch implementation for "TensorLens: End-to-End Transformer Analysis via High-Order Attention Tensors" [ACL 2026]☆49Apr 14, 2026Updated 6 months ago
- Repository for NLP project. Name to be changed when we decide on a project☆17Apr 19, 2022Updated 4 years ago
- MLX implementation of Hierarchical Reasoning Model (HRM) - Adaptive computation for complex reasoning tasks☆29Aug 27, 2025Updated last year
- ADAG: Transluce's MLP neuron-level circuit tracing library☆46Apr 10, 2026Updated 6 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Official code for the paper: "Simple LLM Baselines are Competitive for Model Diffing"☆11Feb 13, 2026Updated 8 months ago
- PyTorch memory allocation visualizer☆76Mar 6, 2026Updated 7 months ago
- prompt engineering experiments with DSPy GEPA and TextGrad☆72Sep 2, 2025Updated last year
- Game of Life on a Toroidal Surface☆16Aug 5, 2025Updated last year
- Training framework with a goal to explore the frontier of sample efficiency of small language models☆101Jan 25, 2026Updated 9 months ago
- ☆19Nov 24, 2025Updated 11 months ago
- ☆10Nov 18, 2024Updated last year
- Evolution Pretraining Fully in Int Formats☆189Feb 25, 2026Updated 8 months ago
- What LLMs Think When You Don’t Tell Them What to Think About?☆15Feb 4, 2026Updated 8 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆12Aug 27, 2025Updated last year
- Training and evaluating with OpenReward☆33Apr 28, 2026Updated 6 months ago
- Training LLMs to Report Their Learned Behaviors☆30Apr 28, 2026Updated 6 months ago
- Open source interpretability artefacts for R1.☆186Apr 21, 2025Updated last year
- ☆65Jul 10, 2025Updated last year
- ☆11Mar 29, 2025Updated last year
- Efficient non-uniform quantization with GPTQ for GGUF☆67Sep 17, 2025Updated last year
- ☆15Apr 26, 2025Updated last year
- A generic deep learning training/testing framework for PyTorch☆14Updated this week
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- Loom TUI and Character Lab for developing AI characters from base models: branch text, curate anthologies, simulate conversations, and ev…☆13Oct 4, 2026Updated 3 weeks ago
- Stack based programming language in C☆20Apr 12, 2023Updated 3 years ago
- X Developer Challenge☆12Apr 25, 2024Updated 2 years ago
- A lightweight, user-friendly data-plane for LLM training.☆43Sep 10, 2025Updated last year
- Streamline on-policy/off-policy distillation workflows in a few lines of code☆112Aug 5, 2026Updated 2 months ago
- Official implementation for DenseMixer: Improving MoE Post-Training with Precise Router Gradient☆68Aug 3, 2025Updated last year
- ☆17Sep 29, 2026Updated last month
- alternative way to calculating self attention☆18May 25, 2024Updated 2 years ago
- [ICML 2025] CommVQ: Commutative Vector Quantization for KV Cache Compression☆27Sep 2, 2025Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- A graph visualization of attention☆56May 20, 2025Updated last year
- Official Code Repositiry for "RaDeR: Reasoning-aware Dense Retrieval Models" accepted at Main Conference EMNLP 2025☆18Jun 23, 2025Updated last year
- Reproducing "Natural Emergent Misalignment from Reward Hacking" (MacDiarmid et al., Anthropic 2025) with open-source models. Includes rew…☆35Oct 5, 2026Updated 3 weeks ago
- A Lean 4 / Mathlib formalization of Coarse-Graining Theory for Elliptic Equations (Armstrong and Kuusi). No sorry, no custom axiom.☆17Oct 5, 2026Updated 3 weeks ago
- Repo for Paper: Discovering Interpretable Algorithms by Decompiling Transformers to RASP☆16May 25, 2026Updated 5 months ago
- MoE training for Me and You and maybe other people☆400Mar 15, 2026Updated 7 months ago
- A toolkit for embedding text datasets with sparse autoencoders☆32Mar 24, 2026Updated 7 months ago