INDEX

Explanations

Job training and employment

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

ルの

-0.06

Leap

-0.06

 cả

-0.06

 hann

-0.06

 तहत

-0.06

 health

-0.06

کو

-0.06

 Cummings

-0.06

 Leap

-0.06

_choose

-0.06

POSITIVE LOGITS

）

0.07

 rede

0.07

 myriad

0.07

///////////////////////////////////////////////////////////////////////////////↵

0.06

 пы

0.06

 Biblical

0.06

 unequal

0.06

+%

0.06

CJK

0.06

辰

0.06

Activations Density 0.037%

Job training and employment

No Comments

No Known Activations