INDEX

Explanations

nervous system

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ake

-0.07

Foo

-0.07

舗

-0.07

Tre

-0.06

إنجليزية

-0.06

clair

-0.06

 bloque

-0.06

GPL

-0.06

ável

-0.06

POSITIVE LOGITS

 nervous

0.09

VIS

0.08

vis

0.07

ardless

0.07

 weaknesses

0.07

 मस

0.07

 Kathy

0.07

rowning

0.07

 Elvis

0.07

................................................................

0.07

Activations Density 0.003%

nervous system

No Comments

No Known Activations