INDEX

Explanations

Titles and politicians

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 turnovers

-0.07

 Larry

-0.07

 bees

-0.06

guy

-0.06

die

-0.06

 gentleman

-0.06

.th

-0.06

Tub

-0.06

 sensors

-0.06

 chops

-0.06

POSITIVE LOGITS

 impuls

0.07

 disproportion

0.07

 embody

0.07

ATT

0.06

'),('

0.06

 enfermed

0.06

Ott

0.06

 MODIFY

0.06

 sistema

0.06

inactive

0.06

Activations Density 0.008%

Titles and politicians

No Comments

No Known Activations