Do Activation Verbalization Methods Convey Privileged Information?
Paper • 2509.13316 • Published
This is the model used to invert Llama-3-8B activations using a T5-Base model (single activation inversion).
The model is used in Do Activation Verbalization Methods Convey Privileged Information? and the base repository used to train this model is from vec2text. Read more of our paper + the underlying vec2text repo for training information.
- Downloads last month
- 37
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
Model tree for millicentli/llama3_inversion_t5-base_single
Base model
google-t5/t5-base