INDEX

Explanations

and

np_max-act · gemini-2.0-flash

The neuron flags tokens commonly used in credits or bibliographic attributions—words like “by,” “and,” “with,” “music,” “lyrics,” “photography,” “book,” “translated,” etc.—marking contributor/credit lines.

oai_token-act-pair · o4-mini Triggered by @xinyanhu8

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

 toaster

-0.08

RefPtr

-0.07

ولد

-0.06

ože

-0.06

낮

-0.06

 basin

-0.06

war

-0.06

ाट

-0.06

gd

-0.06

 manager

-0.06

POSITIVE LOGITS

tract

0.07

xE

0.06

 Concept

0.06

 dread

0.06

<|begin_of_text|>

0.06

arranty

0.06

Obviously

0.06

 Grammar

0.06

 komp

0.06

近

0.06

Activations Density 0.058%

and

The neuron flags tokens commonly used in credits or bibliographic attributions—words like “by,” “and,” “with,” “music,” “lyrics,” “photography,” “book,” “translated,” etc.—marking contributor/credit lines.

No Comments

No Known Activations

and

The neuron flags tokens commonly used in credits or bibliographic attributions—words like “by,” “and,” “with,” “music,” “lyrics,” “photography,” “book,” “translated,” etc.—marking contributor/credit lines.

No Comments

No Known Activations