INDEX

Explanations

footprint

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

lec

-0.08

ialect

-0.07

Sac

-0.06

 Naruto

-0.06

sen

-0.06

orges

-0.06

_female

-0.06

 Subway

-0.06

 Rican

-0.06

POSITIVE LOGITS

 footprint

0.11

 Green

0.07

)"

0.07

 slur

0.06

:)

0.06

 steer

0.06

 SPELL

0.06

 bandwidth

0.06

 політи

0.06

Activations Density 0.003%

footprint

No Comments

No Known Activations