INDEX

Explanations

pronouns

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Random

-0.07

 grows

-0.07

ActionResult

-0.06

 Random

-0.06

_course

-0.06

 Conservative

-0.06

OUSE

-0.06

 برنامه

-0.06

affected

-0.06

 Mojo

-0.06

POSITIVE LOGITS

.toastr

0.07

Σ

0.06

 overrun

0.06

indsay

0.06

couz

0.06

ลาด

0.06

 lanc

0.06

ahrain

0.06

oad

0.06

 Scripts

0.05

Activations Density 0.179%

pronouns

No Comments

No Known Activations

pronouns

No Comments

No Known Activations