INDEX

Explanations

former

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

 Educational

-0.07

 bump

-0.07

 Silence

-0.07

 systemic

-0.07

 september

-0.07

sea

-0.07

getDrawable

-0.07

 coisa

-0.06

ToLocal

-0.06

Seed

-0.06

POSITIVE LOGITS

Former

0.11

 Former

0.11

 former

0.10

.eth

0.07

owner

0.06

'є

0.06

.skin

0.06

(firstName

0.06

ataire

0.06

:title

0.06

Activations Density 0.016%

former

No Comments

No Known Activations