generative-latent-prior/llama1b-layer07-fineweb-1M
收藏Hugging Face2026-02-09 更新2026-03-29 收录
下载链接：
https://hf-mirror.com/datasets/generative-latent-prior/llama1b-layer07-fineweb-1M
下载链接
链接失效反馈官方服务：
资源简介：
---
license: mit
---
## Llama1B 1M Training Activations
This repository contains activation data accompanying the paper __Learning a Generative Meta-Model of LLM Activations__.
* Project page: __https://generative-latent-prior.github.io__
* Code: __https://github.com/g-luo/generative_latent_prior__
## Quick Start
With this data, you can train a GLP on [Llama-3.2-1B](https://huggingface.co/meta-llama/Llama-3.2-1B) activations from Layer 07.
The activations are derived from [FineWeb](https://huggingface.co/datasets/HuggingFaceFW/fineweb).
GLPs are activation diffusion models useful for applications like on-manifold steering and sparse probing.
```python
# download data
huggingface-cli download generative-latent-prior/llama1b-layer07-fineweb-1M \
--repo-type dataset \
--local-dir data/llama1b-layer07-fineweb-1M \
--local-dir-use-symlinks False
# launch training
conda activate glp
python3 glp_train.py config=configs/train_llama1b_static.yaml
```
## Citation
```bibtex
@article{luo2026glp,
title={Learning a Generative Meta-Model of LLM Activations},
author={Grace Luo and Jiahai Feng and Trevor Darrell and Alec Radford and Jacob Steinhardt},
journal={arXiv preprint arXiv:2602.06964},
year={2026}
}
```
提供机构：
generative-latent-prior
