INDEX

Explanations

struct

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

 ears

-0.09

acción

-0.07

ategies

-0.07

apture

-0.07

opper

-0.07

ansom

-0.07

 Wasser

-0.07

ALI

-0.07

 angled

-0.07

 enemies

-0.07

POSITIVE LOGITS

 struct

0.13

	struct

0.12

Struct

0.12

_struct

0.12

struct

0.12

(struct

0.11

 structs

0.10

 Struct

0.10

US

0.08

.struct

0.08

Activations Density 0.008%

struct

No Comments

No Known Activations