INDEX

Explanations

Conference call details

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

 Nurse

-0.07

_pro

-0.06

 ayır

-0.06

_rule

-0.06

 possible

-0.06

 культури

-0.06

нику

-0.06

}*

-0.06

 flexible

-0.06

Exists

-0.06

POSITIVE LOGITS

.epoch

0.07

ABS

0.06

 IHttp

0.06

none

0.06

alah

0.06

 turquoise

0.06

LatLng

0.06

 Boca

0.06

 BinaryTree

0.06

oteca

0.06

Activations Density 0.008%

Conference call details

No Comments

No Known Activations