INDEX

Explanations

political appointments

np_max-act · gemini-2.0-flash

The neuron selectively activates on language describing electoral campaigns and outcomes—mentions of running for office, winning seats, vote counts or percentages, and related political election terminology.

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

Ru

-0.06

byte

-0.06

veget

-0.06

RE

-0.06

宁

-0.06

iktig

-0.06

ERTICAL

-0.06

SOAP

-0.06

Basket

-0.06

 elong

-0.06

POSITIVE LOGITS

 minlength

0.07

prd

0.07

 Seah

0.07

 pleasures

0.06

 $('.

0.06

Osw

0.06

/games

0.06

Firstname

0.06

 Playground

0.06

cs

0.06

Activations Density 0.045%

political appointments

The neuron selectively activates on language describing electoral campaigns and outcomes—mentions of running for office, winning seats, vote counts or percentages, and related political election terminology.

No Comments

No Known Activations