INDEX

Explanations

bills

np_max-act · gemini-2.0-flash

The neuron selectively activates on mentions of medical bills, debts, or other health‐care cost terms.

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

ammo

-0.07

)V

-0.07

_MALLOC

-0.07

ậm

-0.06

_folder

-0.06

 prag

-0.06

}}>

-0.06

〜

-0.06

 orchest

-0.06

 hundred

-0.06

POSITIVE LOGITS

雄

0.07

 이해

0.06

 Zimmer

0.06

Soap

0.06

 Coloring

0.06

Jones

0.06

 Engel

0.06

.depart

0.06

 zeal

0.05

 Bedroom

0.05

Activations Density 0.001%

bills

The neuron selectively activates on mentions of medical bills, debts, or other health‐care cost terms.

No Comments

No Known Activations

bills

The neuron selectively activates on mentions of medical bills, debts, or other health‐care cost terms.

No Comments

No Known Activations