INDEX

Explanations

government

np_max-act · gemini-2.0-flash

The neuron primarily detects occurrences of the word “government” (and its close variants) in text.

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

 Pick

-0.08

 الأك

-0.07

els

-0.06

ully

-0.06

Yak

-0.06

 tricky

-0.06

 solitary

-0.06

ARI

-0.06

iky

-0.06

 Circle

-0.06

POSITIVE LOGITS

 government

0.14

 Government

0.13

Government

0.12

gov

0.11

Gov

0.11

gov

0.11

 governments

0.10

Gov

0.10

GV

0.09

 governmental

0.08

Activations Density 0.020%

government

The neuron primarily detects occurrences of the word “government” (and its close variants) in text.

No Comments

No Known Activations