science-of-finetuning
/

Llama-3.2-1B-L8-mu3.6e-02-lr1e-04-local-shuffling-CrosscoderLoss

model_hub_mixin

pytorch_model_hub_mixin

Model card Files Files and versions Community

This model has been pushed to the Hub using the PytorchModelHubMixin integration:

Code: [More Information Needed]
Paper: [More Information Needed]
Docs: [More Information Needed]

Downloads last month: 55

Safetensors

Model size

537M params

Tensor type

F32

·

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Collection including science-of-finetuning/Llama-3.2-1B-L8-mu3.6e-02-lr1e-04-local-shuffling-CrosscoderLoss

Base-Chat middle layer Crosscoders

A collection of crosscoders trained for our paper "Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning" https://arxiv.org/abs/2504.0 • 6 items • Updated 7 days ago