INDEX

Explanations

code and math

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

 reflux

-0.08

Default

-0.07

 Default

-0.07

 Difficulty

-0.06

 uniformly

-0.06

clo

-0.06

 Custom

-0.06

(detail

-0.06

filepath

-0.06

 indexPath

-0.06

POSITIVE LOGITS

.MouseEvent

0.07

(repository

0.06

 تومان

0.06

 iNdEx

0.06

.zh

0.06

/admin

0.06

 seventy

0.06

;amp

0.06

(layout

0.06

 يو

0.06

Activations Density 0.019%

code and math

No Comments

No Known Activations