INDEX

Explanations

exhibits and museums

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

 Серг

-0.06

Weights

-0.06

 Oliver

-0.06

Website

-0.06

uer

-0.06

_problem

-0.06

 truthful

-0.06

 suppliers

-0.06

 služby

-0.06

_:

-0.06

POSITIVE LOGITS

 ascertain

0.07

_timezone

0.07

 indispens

0.06

 elevate

0.06

 환경

0.06

Met

0.06

 escalating

0.06

 lowering

0.06

 awkward

0.06

STD

0.06

Activations Density 0.034%

exhibits and museums

No Comments

No Known Activations