INDEX

Explanations

punctuation follows

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_27/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.27.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Το

-0.07

 Wells

-0.06

,u

-0.06

Robot

-0.06

"><?=$

-0.06

 Every

-0.06

.LayoutParams

-0.06

 restarted

-0.06

 Nietzsche

-0.06

.directive

-0.06

POSITIVE LOGITS

_paper

0.07

 alumni

0.06

ΠΑ

0.06

 Borg

0.06

_workers

0.06

gorit

0.06

 ingestion

0.06

better

0.06

enie

0.06

PAR

0.06

Activations Density 0.649%

punctuation follows

No Comments

No Known Activations