INDEX

Explanations

Coding related (foreign language)

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

Sale

-0.07

 Nissan

-0.06

 pride

-0.06

亭

-0.06

 jelly

-0.06

(arg

-0.06

 Nation

-0.06

 deserves

-0.06

 rape

-0.06

POSITIVE LOGITS

 unrealistic

0.07

 ISSUE

0.07

开始

0.06

(Self

0.06

 abbreviated

0.06

 arkadaş

0.06

变

0.06

거래

0.06

ios

0.06

ování

0.06

Activations Density 0.061%

Coding related (foreign language)

No Comments

No Known Activations