INDEX

Explanations

performance

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

 Jennifer

-0.07

 mujeres

-0.07

 Buddh

-0.07

子供

-0.06

 cannabinoids

-0.06

 Night

-0.06

unny

-0.06

Jennifer

-0.06

 rhyme

-0.06

 приступ

-0.06

POSITIVE LOGITS

 kaliteli

0.07

 sécur

0.07

 Bachelor

0.07

checkpoint

0.06

Fam

0.06

ี.

0.06

prix

0.06

ACM

0.06

SCALL

0.06

Activations Density 0.017%

performance

No Comments

No Known Activations

performance

No Comments

No Known Activations