INDEX

Explanations

)

np_max-act · gemini-2.0-flash

The neuron specifically activates on parenthesis characters (especially “)” and “(”).

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

 Spiel

-0.06

paired

-0.06

chnitt

-0.06

 بالا

-0.06

MOZ

-0.06

 dữ

-0.06

Features

-0.06

 wolves

-0.06

 tratamiento

-0.06

POSITIVE LOGITS

Rib

0.06

	Close

0.06

ptive

0.06

 fallback

0.06

ी

0.06

 Орг

0.06

 intriguing

0.06

imb

0.06

letters

0.05

 setIs

0.05

Activations Density 0.005%

)

The neuron specifically activates on parenthesis characters (especially “)” and “(”).

No Comments

No Known Activations