INDEX

Explanations

children and babies

np_max-act · gemini-2.0-flash

This neuron detects mentions of the patient—specifically the word “child” (and its possessive form).

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

_land

-0.06

ying

-0.06

 sera

-0.06

 Orchestra

-0.06

Todo

-0.06

 yani

-0.06

 tube

-0.06

AQ

-0.06

shirt

-0.06

 Worce

-0.06

POSITIVE LOGITS

дается

0.06

_{}

0.06

 editors

0.06

 полити

0.06

-lnd

0.06

apt

0.06

 توم

0.06

 grandson

0.06

重

0.06

 Aleppo

0.06

Activations Density 0.010%

children and babies

This neuron detects mentions of the patient—specifically the word “child” (and its possessive form).

No Comments

No Known Activations