INDEX

Explanations

children

np_max-act · gemini-2.0-flash

The neuron activates on mentions of households “had children under the age of 18,” i.e. it finds the phrase indicating children under eighteen.

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

_slope

-0.07

 denom

-0.07

Spain

-0.07

ί

-0.07

 roli

-0.07

ografia

-0.07

 Spain

-0.07

ancers

-0.07

 імені

-0.06

 форме

-0.06

POSITIVE LOGITS

aque

0.06

DOCUMENT

0.06

indsay

0.06

HL

0.06

${

0.06

 remains

0.06

 continued

0.06

==>

0.06

 createUser

0.06

Activations Density 0.000%

children

The neuron activates on mentions of households “had children under the age of 18,” i.e. it finds the phrase indicating children under eighteen.

No Comments

No Known Activations