INDEX

Explanations

canada

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Lips

-0.08

 mills

-0.07

Sem

-0.07

sep

-0.07

tro

-0.07

 descending

-0.06

 Browse

-0.06

(im

-0.06

 internship

-0.06

(out

-0.06

POSITIVE LOGITS

 Canada

0.11

Canada

0.10

 Canadian

0.09

Canadian

0.09

uely

0.08

 Canadians

0.08

 Toronto

0.07

 Manitoba

0.07

contin

0.07

 паци

0.07

Activations Density 0.009%

canada

No Comments

No Known Activations