INDEX

Explanations

patients

np_max-act · gemini-2.0-flash

This neuron detects mentions of human study subject groups (e.g. “patients,” “healthy volunteers,” etc.).

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ست

-0.07

SEM

-0.06

scenario

-0.06

औ

-0.06

 composition

-0.06

 alleg

-0.06

 Generic

-0.06

 poverty

-0.06

ソ

-0.06

ств

-0.06

POSITIVE LOGITS

 telemetry

0.07

ightly

0.07

 tuberculosis

0.06

 kurul

0.06

ğinin

0.06

)init

0.06

Discuss

0.06

Asked

0.06

 QtCore

0.06

 Interior

0.06

Activations Density 0.054%

patients

This neuron detects mentions of human study subject groups (e.g. “patients,” “healthy volunteers,” etc.).

No Comments

No Known Activations