INDEX

Explanations

communication

np_max-act · gemini-2.0-flash

The neuron detects tokens related to communication or information exchange (e.g. “communication,” “exchange,” “interdisciplinary”).

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

prod

-0.07

 ΔΗΜ

-0.06

 берез

-0.06

 глу

-0.06

su

-0.06

úng

-0.06

 Pills

-0.06

 ULONG

-0.06

лаб

-0.06

mer

-0.06

POSITIVE LOGITS

 Yahoo

0.07

 Clifford

0.07

íf

0.07

@Json

0.07

 게임

0.06

 parlament

0.06

 warfare

0.06

.ManyToMany

0.06

typedef

0.06

 абсолют

0.06

Activations Density 0.022%

communication

The neuron detects tokens related to communication or information exchange (e.g. “communication,” “exchange,” “interdisciplinary”).

No Comments

No Known Activations