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.
☆625Updated 7 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☆690Updated last year
- Visualize the intermediate output of Mistral 7B☆375Updated 9 months ago
- A library for making RepE control vectors☆651Updated last month
- Bayesian Optimization as a Coverage Tool for Evaluating LLMs. Accurate evaluation (benchmarking) that's 10 times faster with just a few l…☆286Updated last month
- Felafax is building AI infra for non-NVIDIA GPUs☆568Updated 9 months ago
- Open weights language model from Google DeepMind, based on Griffin.☆652Updated 4 months ago
- A multi-player tournament benchmark that tests LLMs in social reasoning, strategy, and deception. Players engage in public and private co…☆290Updated 2 months ago
- Visualizing the internal board state of a GPT trained on chess PGN strings, and performing interventions on its internal board state and …☆216Updated 11 months ago
- Achieve the llama3 inference step-by-step, grasp the core concepts, master the process derivation, implement the code.☆609Updated 8 months ago
- Official codebase for the paper "Beyond A* Better Planning with Transformers via Search Dynamics Bootstrapping".☆374Updated last year
- A scientific instrument for investigating latent spaces☆732Updated 5 months ago
- Absolute minimalistic implementation of a GPT-like transformer using only numpy (<650 lines).☆254Updated last year
- Finetune llama2-70b and codellama on MacBook Air without quantization☆449Updated last year
- A pure NumPy implementation of Mamba.☆223Updated last year
- ☆234Updated 7 months ago
- An implementation of bucketMul LLM inference☆223Updated last year
- ☆248Updated last year
- Dead Simple LLM Abliteration☆232Updated 8 months ago
- Code behind Arxiv Papers☆530Updated last year
- An interactive HTML pretty-printer for machine learning research in IPython notebooks.☆448Updated 2 months ago
- a small code base for training large models☆309Updated 5 months ago
- ☆443Updated last month
- ☆746Updated last year
- Things you can do with the token embeddings of an LLM☆1,448Updated 6 months ago
- A BERT that you can train on a (gaming) laptop.☆207Updated 2 years ago
- Stop messing around with finicky sampling parameters and just use DRµGS!☆357Updated last year
- The Fast Vector Similarity Library is designed to provide efficient computation of various similarity measures between vectors.☆404Updated 7 months ago
- Implement recursion using English as the programming language and an LLM as the runtime.☆236Updated 2 years ago
- ☆116Updated 8 months ago
- a curated list of data for reasoning ai☆140Updated last year