INDEX

Explanations

Number

np_max-act · gemini-2.0-flash

The neuron detects tokens that specify or reference creating a numbered list or ordered steps.

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

優

-0.07

�

-0.07

Guild

-0.06

-С

-0.06

 binary

-0.06

 audiences

-0.06

Ell

-0.06

ेल

-0.06

 mediator

-0.06

jing

-0.06

POSITIVE LOGITS

?
↵

0.07

mode

0.07

);"

0.06

oolStrip

0.06

 numbered

0.06

tober

0.06

;"↵

0.06

/trunk

0.06

 Alphabet

0.06

Activations Density 0.011%

Number

The neuron detects tokens that specify or reference creating a numbered list or ordered steps.

No Comments

No Known Activations