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☆742Updated this week
- Minimal LLM inference in Rust☆1,032Oct 24, 2024Updated 2 years ago
- Training Sparse Autoencoders on Language Models☆1,581Updated this week
- pingcap/autoflow is a Graph RAG based and conversational knowledge base tool built with TiDB Serverless Vector Storage. Demo: https://tid…☆2,982Updated this week
- A JAX research toolkit for building, editing, and visualizing neural networks.☆1,899Jun 22, 2025Updated last year
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- OpenCV+YOLO+LLAVA powered video surveillance system☆793Oct 21, 2025Updated last year
- Things you can do with the token embeddings of an LLM☆1,449Dec 1, 2025Updated 11 months ago
- Felafax is building AI infra for non-NVIDIA GPUs☆568Jan 24, 2025Updated last year
- Entropy Based Sampling and Parallel CoT Decoding☆3,435Nov 13, 2024Updated last year
- LLM Analytics☆715Jul 8, 2026Updated 3 months ago
- A library for mechanistic interpretability of GPT-style language models☆4,051Updated this week
- ☆435Aug 21, 2025Updated last year
- Grandmaster-Level Chess Without Search☆665Jan 10, 2025Updated last year
- Structured Outputs☆16,005Sep 21, 2026Updated last month
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- ☆584Aug 13, 2026Updated 2 months ago
- Animating R1's thoughts.☆378Feb 17, 2025Updated last year
- ☆196May 5, 2025Updated last year
- ☆186May 1, 2026Updated 6 months ago
- Proof of thought : LLM-based reasoning using Z3 theorem proving with multiple backend support (SMT2 and JSON DSL)☆377Oct 31, 2026Updated last week
- A comprehensive suite of tools, built to liberate science by making the creation, evaluation, and dissemination of research more transpar…☆253Aug 8, 2025Updated last year
- Fine-tune LLM agents with online reinforcement learning☆1,256Mar 19, 2024Updated 2 years ago
- ☆4,124Apr 15, 2026Updated 6 months ago
- DiscoGrad - automatically differentiate across conditional branches in C++ programs☆210Sep 12, 2024Updated 2 years 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.
- Dead Simple LLM Abliteration☆286Mar 2, 2026Updated 8 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆281Updated this week
- Fully neural approach for text chunking☆420Oct 23, 2025Updated last year
- A framework for training, analyzing, and visualizing sparse autoencoders and related interpretability methods☆232Oct 4, 2026Updated last month
- High-Performance Implementation of OpenAI's TikToken.☆474Jul 3, 2025Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆278Feb 27, 2026Updated 8 months ago
- Achieve the llama3 inference step-by-step, grasp the core concepts, master the process derivation, implement the code.☆630Feb 24, 2025Updated last year
- A Bulletproof Way to Generate Structured JSON from Language Models☆4,938Feb 24, 2024Updated 2 years ago
- Deep Reinforcement Learning: Zero to Hero!☆2,293May 26, 2026Updated 5 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.
- RAG that intelligently adapts to your use case, data, and queries☆3,968Nov 1, 2025Updated last year
- Radient turns many data types (not just text) into vectors for similarity search, RAG, regression analysis, and more.☆281Mar 2, 2026Updated 8 months ago
- Recipes to scale inference-time compute of open models☆1,133Sep 23, 2026Updated last month
- Sparse Autoencoder Training Library☆59May 1, 2025Updated last year
- Docker-based inference engine for AMD GPUs☆233Oct 7, 2024Updated 2 years ago
- A reimplementation of Stable Diffusion 3.5 in pure PyTorch☆706Jun 14, 2025Updated last year
- Everything about the SmolLM and SmolVLM family of models☆3,947Oct 6, 2026Updated last month