INDEX

Explanations

Transport

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.23.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-entry

-0.07

ization

-0.07

ギ

-0.06

cctor

-0.06

Assertion

-0.06

 aplicación

-0.06

くれる

-0.06

 erad

-0.06

POSITIVE LOGITS

	select

0.07

#----------------------------------------------------------------------------

0.07

Misc

0.07

.Fill

0.06

SetText

0.06

UNS

0.06

("//*[@

0.06

RR

0.06

 nodeId

0.06

(ids

0.06

Activations Density 0.006%

Transport

No Comments

No Known Activations