INDEX

Explanations

punctuation

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

 centerX

-0.07

OTS

-0.07

 peanut

-0.07

_mul

-0.07

_OUT

-0.06

 trailing

-0.06

CLE

-0.06

.RemoveAll

-0.06

 assemblies

-0.06

ULE

-0.06

POSITIVE LOGITS

("----------------

0.07

 ordin

0.06

Inventory

0.06

.desktop

0.06

uis

0.06

 día

0.06

↵↵

0.06

!”↵↵

0.06

”↵↵

0.06

 країн

0.06

Activations Density 0.086%

punctuation

No Comments

No Known Activations