INDEX

Explanations

News articles

np_max-act · gemini-2.0-flash

The neuron detects promotional or marketing terms—especially calls to action and bonus/offer words (e.g. “free,” “App,” “spins,” “coins,” “device”).

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

.tiles

-0.06

(vec

-0.06

''"

-0.06

 Hands

-0.06

ення

-0.06

.shop

-0.06

Bun

-0.06

 Elephant

-0.06

 SizedBox

-0.06

 cyclists

-0.06

POSITIVE LOGITS

CO

0.07

 audition

0.07

 uphe

0.07

 president

0.07

 SCIP

0.06

"]

0.06

}$/

0.06

-Allow

0.06

 arise

0.06

 Müdürlüğü

0.06

Activations Density 0.271%

News articles

The neuron detects promotional or marketing terms—especially calls to action and bonus/offer words (e.g. “free,” “App,” “spins,” “coins,” “device”).

No Comments

No Known Activations