INDEX

Explanations

Text Snippets

np_max-act · gemini-2.0-flash

The neuron responds to the structural elements of multiple-choice questions—e.g. question marks, parentheses, option numbers, colons, and other formatting tokens used to list answer choices.

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

Air

-0.06

kne

-0.06

 finances

-0.06

air

-0.06

 Ning

-0.06

EG

-0.06

 URLRequest

-0.06

 Ethics

-0.06

 сделать

-0.06

"))↵↵

-0.06

POSITIVE LOGITS

اطعة

0.08

ульт

0.07

咨

0.07

َة

0.07

�m

0.07

 Dere

0.07

ayıf

0.06

 buscar

0.06

.Compute

0.06

ges

0.06

Activations Density 0.009%

Text Snippets

The neuron responds to the structural elements of multiple-choice questions—e.g. question marks, parentheses, option numbers, colons, and other formatting tokens used to list answer choices.

No Comments

No Known Activations

Text Snippets

The neuron responds to the structural elements of multiple-choice questions—e.g. question marks, parentheses, option numbers, colons, and other formatting tokens used to list answer choices.

No Comments

No Known Activations