INDEX

Explanations

amygdala

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

htdocs

-0.07

 tělo

-0.07

.HORIZONTAL

-0.06

 walkers

-0.06

 strany

-0.06

 Cohen

-0.06

_PATH

-0.06

Tester

-0.06

 náměstí

-0.06

POSITIVE LOGITS

rng

0.06

rng

0.06

lear

0.06

 contribute

0.06

 discomfort

0.06

 aggravated

0.06

 amount

0.06

)|(

0.06

muj

0.06

 Вы

0.06

Activations Density 0.001%

amygdala

No Comments

No Known Activations

amygdala

No Comments

No Known Activations