Downloads · 30 days
0
Koalacrown/llama3.1-8b-it-cognitive-actions-sae-l11
llama3.1-8b-it-cognitive-actions-sae-l11 is a machine learning model from Koalacrown. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This is a Sparse Autoencoder (SAE) trained on layer 11 activations from LLaMA-3.1-8B-Instruct using the FAST methodology.
Downloads · 30 days
0
Access
Public
Updated Oct 4, 2025
Repo size
8.4 MB
Likes
0
Public
Click a slice to open those files.
.pt8.4 MB · 93%
From the Hugging Face model README
This is a Sparse Autoencoder (SAE) trained on layer 11 activations from LLaMA-3.1-8B-Instruct using the FAST methodology.
from hypothesaes.sae import load_model
sae = load_model("Koalacrown/llama3.1-8b-it-cognitive-actions-sae-l11")
features = sae.get_activations(activations)
Trained using HypotheSAEs with the following configuration:
If you use this SAE, please cite the FAST methodology and HypotheSAEs.