INDEX

Explanations

crimes

np_max-act · gemini-2.0-flash

This neuron responds to mentions of specific official agencies or specialized law-enforcement and emergency-response unit names.

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

}`,↵

-0.08

 Hose

-0.08

 summons

-0.07

 Дем

-0.07

 overclock

-0.07

_CLEAN

-0.07

ограм

-0.06

 racked

-0.06

 scape

-0.06

 галуз

-0.06

POSITIVE LOGITS

@SuppressWarnings

0.06

 машин

0.06

过去

0.06

 versa

0.06

UsageId

0.06

lag

0.06

 χρόνια

0.06

 lizard

0.06

instead

0.06

-law

0.06

Activations Density 0.031%

crimes

This neuron responds to mentions of specific official agencies or specialized law-enforcement and emergency-response unit names.

No Comments

No Known Activations