PaulPauls / llama3_interpretability_saeLinks
A complete end-to-end pipeline for LLM interpretability with sparse autoencoders (SAEs) using Llama 3.2, written in pure PyTorch and fully reproducible.
☆622Updated 5 months ago
Alternatives and similar repositories for llama3_interpretability_sae
Users that are interested in llama3_interpretability_sae are comparing it to the libraries listed below
Sorting:
- LLM Analytics☆677Updated 10 months ago
- Felafax is building AI infra for non-NVIDIA GPUs☆567Updated 7 months ago
- Visualize the intermediate output of Mistral 7B☆368Updated 7 months ago
- Bayesian Optimization as a Coverage Tool for Evaluating LLMs. Accurate evaluation (benchmarking) that's 10 times faster with just a few l…☆286Updated 3 weeks ago
- A library for making RepE control vectors☆624Updated 7 months ago
- Open weights language model from Google DeepMind, based on Griffin.☆647Updated 2 months ago
- Official codebase for the paper "Beyond A* Better Planning with Transformers via Search Dynamics Bootstrapping".☆373Updated last year
- A pure NumPy implementation of Mamba.☆224Updated last year
- An interactive HTML pretty-printer for machine learning research in IPython notebooks.☆439Updated 2 weeks ago
- ☆248Updated last year
- Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and …☆210Updated 9 months ago
- Code behind Arxiv Papers☆527Updated last year
- ☆745Updated last year
- ☆220Updated 5 months ago
- ☆401Updated this week
- A scientific instrument for investigating latent spaces☆722Updated 3 months ago
- Code to train and evaluate Neural Attention Memory Models to obtain universally-applicable memory systems for transformers.☆318Updated 10 months ago
- Dead Simple LLM Abliteration☆231Updated 6 months ago
- A multi-player tournament benchmark that tests LLMs in social reasoning, strategy, and deception. Players engage in public and private co…☆290Updated last week
- a small code base for training large models☆309Updated 3 months ago
- Implement recursion using English as the programming language and an LLM as the runtime.☆239Updated 2 years ago
- Achieve the llama3 inference step-by-step, grasp the core concepts, master the process derivation, implement the code.☆605Updated 6 months ago
- A BERT that you can train on a (gaming) laptop.☆209Updated last year
- Absolute minimalistic implementation of a GPT-like transformer using only numpy (<650 lines).☆253Updated last year
- a curated list of data for reasoning ai☆137Updated last year
- Grandmaster-Level Chess Without Search☆589Updated 7 months ago
- Things you can do with the token embeddings of an LLM☆1,445Updated 4 months ago
- An implementation of bucketMul LLM inference☆222Updated last year
- Finetune llama2-70b and codellama on MacBook Air without quantization☆448Updated last year
- OpenAI's Structured Outputs with Logprobs☆182Updated 2 months ago