A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.
☆641Mar 23, 2025Updated last year
Alternatives and similar repositories for llama3_interpretability_sae
Users that are interested in llama3_interpretability_sae are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Sparsify transformers with SAEs and transcoders☆741Updated this week
- Minimal LLM inference in Rust☆1,033Oct 24, 2024Updated last year
- pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tid…☆2,978Apr 27, 2026Updated 5 months ago
- Felafax is building AI infra for non-NVIDIA GPUs☆569Jan 24, 2025Updated last year
- OpenCV+YOLO+LLAVA powered video surveillance system☆792Oct 21, 2025Updated 11 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.
- A JAX research toolkit for building, editing, and visualizing neural networks.☆1,899Jun 22, 2025Updated last year
- Training Sparse Autoencoders on Language Models☆1,563Updated this week
- ☆584Aug 13, 2026Updated 2 months ago
- Things you can do with the token embeddings of an LLM☆1,450Dec 1, 2025Updated 10 months ago
- LLM Analytics☆715Jul 8, 2026Updated 3 months ago
- Entropy Based Sampling and Parallel CoT Decoding☆3,430Nov 13, 2024Updated last year
- Structured Outputs☆15,949Sep 21, 2026Updated 3 weeks ago
- Proof of thought : LLM-based reasoning using Z3 theorem proving with multiple backend support (SMT2 and JSON DSL)☆377Jul 7, 2026Updated 3 months ago
- Achieve the llama3 inference step-by-step, grasp the core concepts, master the process derivation, implement the code.☆629Feb 24, 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.
- ☆196May 5, 2025Updated last year
- Fully neural approach for text chunking☆421Oct 23, 2025Updated 11 months ago
- A library for mechanistic interpretability of GPT-style language models☆3,975Updated this week
- Grandmaster-Level Chess Without Search☆664Jan 10, 2025Updated last year
- RAG that intelligently adapts to your use case, data, and queries☆3,966Nov 1, 2025Updated 11 months ago
- DiscoGrad - automatically differentiate across conditional branches in C++ programs☆210Sep 12, 2024Updated 2 years ago
- ☆4,123Apr 15, 2026Updated 6 months ago
- ai for jq☆250Sep 20, 2024Updated 2 years ago
- Deep Reinforcement Learning: Zero to Hero!☆2,294May 26, 2026Updated 4 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.
- Everything about the SmolLM and SmolVLM family of models☆3,926Oct 6, 2026Updated last week
- ☆186May 1, 2026Updated 5 months ago
- Animating R1's thoughts.☆378Feb 17, 2025Updated last year
- High-Performance Implementation of OpenAI's TikToken.☆475Jul 3, 2025Updated last year
- A comprehensive suite of tools, built to liberate science by making the creation, evaluation, and dissemination of research more transpar…☆254Aug 8, 2025Updated last year
- Fine-tune LLM agents with online reinforcement learning☆1,253Mar 19, 2024Updated 2 years ago
- Sparse Autoencoder Training Library☆58May 1, 2025Updated last year
- ☆434Aug 21, 2025Updated last year
- Radient turns many data types (not just text) into vectors for similarity search, RAG, regression analysis, and more.☆281Mar 2, 2026Updated 7 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.
- A library for making RepE control vectors☆760Sep 24, 2025Updated last year
- Docker-based inference engine for AMD GPUs☆234Oct 7, 2024Updated 2 years ago
- A Bulletproof Way to Generate Structured JSON from Language Models☆4,937Feb 24, 2024Updated 2 years ago
- A guidance language for controlling large language models.☆21,800May 21, 2026Updated 4 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆276Feb 27, 2026Updated 7 months ago
- Dead Simple LLM Abliteration☆284Mar 2, 2026Updated 7 months ago
- Seamlessly integrate LLMs as Python functions☆2,428Mar 11, 2026Updated 7 months ago