---
library_name: saelens
license: apache-2.0
datasets:
- Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024
---

# Llama-3-8B SAEs (layer 25, Post-MLP Residual Stream)

## Introduction

We train a Gated SAE on the post-MLP residual stream of the 25th layer of [Llama-3-8b-instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) model. The width of SAE hidden dimensions is 65536 (x16). 

The SAE is trained with 500M tokens from the [OpenWebText corpus](https://huggingface.co/datasets/Juliushanhanhan/openwebtext-1b-llama3-tokenized-cxt-1024).

Feature visualizations are hosted at https://www.neuronpedia.org/llama3-8b-it. The wandb run is recorded [here](https://wandb.ai/jiatongg/sae_semantic_entropy/runs/ruuu0izg?nw=nwuserjiatongg).

## Load the Model


This repository contains the following SAEs:
- blocks.25.hook_resid_post

Load these SAEs using SAELens as below:
```python
from sae_lens import SAE

sae, cfg_dict, sparsity = SAE.from_pretrained("Juliushanhanhan/llama-3-8b-it-res", "<sae_id>")
```

## Citation

```
@misc {jiatong_han_2024,
	author       = { {Jiatong Han} },
	title        = { llama-3-8b-it-res (Revision 53425c3) },
	year         = 2024,
	url          = { https://huggingface.co/Juliushanhanhan/llama-3-8b-it-res },
	doi          = { 10.57967/hf/2889 },
	publisher    = { Hugging Face }
}
```