INDEX

Explanations

to

np_max-act · gemini-2.0-flash

This neuron detects instances of being accustomed or desensitized to something, as in “desensitized to horrific violence” or “used to the horrible conditions.”

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

 failed

-0.07

GroupName

-0.07

 fail

-0.07

ificates

-0.06

 onemoc

-0.06

 insert

-0.06

 شرکت

-0.06

sha

-0.06

 interference

-0.06

 contenders

-0.06

POSITIVE LOGITS

oron

0.08

 accustomed

0.07

:)

0.07

 alış

0.06

«

0.06

otton

0.06

 Guinea

0.06

owi

0.06

bò

0.06

 worn

0.06

Activations Density 0.009%

to

This neuron detects instances of being accustomed or desensitized to something, as in “desensitized to horrific violence” or “used to the horrible conditions.”

No Comments

No Known Activations