INDEX

Explanations

r

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

опис

-0.08

SUB

-0.08

 undo

-0.07

ología

-0.07

 наче

-0.07

Marcus

-0.07

nad

-0.07

想

-0.07

 Mend

-0.07

 Form

-0.07

POSITIVE LOGITS

 Electrical

0.11

 electrical

0.10

 Electric

0.10

 electric

0.09

 electricity

0.09

 elektr

0.09

 electr

0.08

Electric

0.08

 ELECT

0.08

 élect

0.07

Activations Density 0.024%

r

No Comments

No Known Activations

r

No Comments

No Known Activations