INDEX

Explanations

Judge

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

 webs

-0.07

lian

-0.07

 Systems

-0.06

mouth

-0.06

 deviations

-0.06

 sight

-0.06

iments

-0.06

oms

-0.06

 caravan

-0.06

 visions

-0.06

POSITIVE LOGITS

 judge

0.12

Judge

0.08

 judges

0.08

 Judge

0.08

 judged

0.07

 courte

0.07

Const

0.07

judge

0.07

de

0.07

.nextElement

0.07

Activations Density 0.007%

Judge

No Comments

No Known Activations

Judge

No Comments

No Known Activations