INDEX

Explanations

and

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

نوع

-0.07

 번째

-0.07

zek

-0.06

_ADV

-0.06

?>"><

-0.06

arParams

-0.06

<Product

-0.06

isms

-0.06

POSITIVE LOGITS

 meantime

0.07

 trucks

0.07

Cu

0.07

 Jensen

0.07

 중앙

0.06

 Pruitt

0.06

 copper

0.06

 rates

0.06

 ubuntu

0.06

Activations Density 0.103%

and

No Comments

No Known Activations