INDEX

Explanations

automobiles and/or technology

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 incidental

-0.07

지도

-0.07

ité

-0.07

 MonoBehaviour

-0.06

 contracted

-0.06

 Ezek

-0.06

Laura

-0.06

遺

-0.06

Rick

-0.06

ิศ

-0.06

POSITIVE LOGITS

 spoj

0.07

0.06

_nom

0.06

 olmuştur

0.06

apple

0.06

 '').

0.06

(html

0.06

]-$

0.06

サー

0.06

Activations Density 0.048%

automobiles and/or technology

No Comments

No Known Activations

automobiles and/or technology

No Comments

No Known Activations