README.md

---
language: en
library_name: mlsae
license: mit
tags:
- arxiv:2409.04185
- model_hub_mixin
- pytorch_model_hub_mixin
---

# Model Card for tim-lawson/mlsae-Llama-3.2-3B-x64-k32

A Multi-Layer Sparse Autoencoder (MLSAE) trained on the residual stream activation
vectors from [meta-llama/Llama-3.2-3B](https://huggingface.co/meta-llama/Llama-3.2-3B) with an
expansion factor of R = 64 and sparsity k = 32, over 1 billion
tokens from [monology/pile-uncopyrighted](https://huggingface.co/datasets/monology/pile-uncopyrighted).


This model is a PyTorch TopKSAE module, which does not include the underlying
transformer.

  
### Model Sources

- **Repository:** <https://github.com/tim-lawson/mlsae>
- **Paper:** <https://arxiv.org/abs/2409.04185>
- **Weights & Biases:** <https://wandb.ai/timlawson-/mlsae>

## Citation

**BibTeX:**

```bibtex
@misc{lawson_residual_2024,
  title         = {Residual {{Stream Analysis}} with {{Multi-Layer SAEs}}},
  author        = {Lawson, Tim and Farnik, Lucy and Houghton, Conor and Aitchison, Laurence},
  year          = {2024},
  month         = oct,
  number        = {arXiv:2409.04185},
  eprint        = {2409.04185},
  primaryclass  = {cs},
  publisher     = {arXiv},
  doi           = {10.48550/arXiv.2409.04185},
  urldate       = {2024-10-08},
  archiveprefix = {arXiv}
}
```