INDEX

Explanations

characteristic

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

Un

-0.07

increase

-0.07

 Increase

-0.07

(it

-0.07

े↵

-0.06

More

-0.06

 grow

-0.06

 decreased

-0.06

 completely

-0.06

POSITIVE LOGITS

 signature

0.09

 trademark

0.08

 Signature

0.07

matcher

0.07

.SetText

0.07

寶

0.07

их

0.07

Signature

0.07

 distinctive

0.07

μιλος

0.06

Activations Density 0.019%

characteristic

No Comments

No Known Activations