INDEX

Explanations

article corrections

np_max-act · gemini-2.0-flash

The neuron detects the standard correction-notice phrasing in scholarly articles—e.g. “In the original published version…,” “incorrectly,” “error,” and “corrected.”

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

 Manga

-0.07

CCC

-0.07

 caul

-0.07

_square

-0.06

Nó

-0.06

caret

-0.06

 детей

-0.06

Ted

-0.06

 bishops

-0.06

POSITIVE LOGITS

ATP

0.07

.ACTION

0.07

 );↵↵

0.07

 основе

0.07

.expression

0.07

VisualStyle

0.06

�

0.06

.`);↵

0.06

)↵↵↵

0.06

 */↵↵↵

0.06

Activations Density 0.008%

article corrections

The neuron detects the standard correction-notice phrasing in scholarly articles—e.g. “In the original published version…,” “incorrectly,” “error,” and “corrected.”

No Comments

No Known Activations