INDEX

Explanations

medical emergencies and death

np_max-act · gemini-2.0-flash

This neuron detects descriptions of medical emergencies and resuscitation events, especially references to stopped vital signs and revival efforts.

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

 Pickup

-0.06

 convenience

-0.06

стри

-0.06

ouchers

-0.06

 compressor

-0.06

/operator

-0.06

 له

-0.06

Greg

-0.06

:"↵

-0.05

股份有限公司

-0.05

POSITIVE LOGITS

-threat

0.07

_valid

0.07

warnings

0.07

 전용면적

0.07

 sparked

0.06

.quote

0.06

Displays

0.06

 неболь

0.06

(datetime

0.06

 Đà

0.06

Activations Density 0.014%

medical emergencies and death

This neuron detects descriptions of medical emergencies and resuscitation events, especially references to stopped vital signs and revival efforts.

No Comments

No Known Activations

medical emergencies and death

This neuron detects descriptions of medical emergencies and resuscitation events, especially references to stopped vital signs and revival efforts.

No Comments

No Known Activations