INDEX

Explanations

medical treatments

np_max-act · gemini-2.0-flash

The main thing this neuron does is detect mentions of clinical life-sustaining treatments and critical medical procedures.

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

	BOOL

-0.07

gia

-0.07

ki

-0.07

 đọ

-0.06

-max

-0.06

pep

-0.06

 errores

-0.06

getUrl

-0.06

 Logged

-0.06

 sche

-0.06

POSITIVE LOGITS

-standard

0.07

 "));↵

0.06

?>
↵

0.06

crear

0.06

.setPrototypeOf

0.06

_shell

0.06

}");
↵

0.06

_|

0.06

 baise

0.06

","

0.06

Activations Density 0.020%

medical treatments

The main thing this neuron does is detect mentions of clinical life-sustaining treatments and critical medical procedures.

No Comments

No Known Activations