INDEX

Explanations

Foreign language or code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.27.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Coordinate

-0.07

_directory

-0.07

 unify

-0.06

TextBox

-0.06

_radi

-0.06

Turn

-0.06

-top

-0.06

 prognosis

-0.06

etest

-0.06

细胞

-0.06

POSITIVE LOGITS

allocated

0.07

oggle

0.07

ascar

0.07

/************************************************************************************************

0.06

(`<

0.06

kiye

0.06

>");↵↵

0.06

”,

0.06

够

0.06

FXML

0.06

Activations Density 0.045%

Foreign language or code

No Comments

No Known Activations