INDEX

Explanations

provides/allows something else

np_max-act · gemini-2.0-flash

This neuron fires on service-oriented verbs that describe features or capabilities (e.g. “adds,” “provides,” “uses,” “allows,” “gives”).

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

aji

-0.07

кові

-0.06

=find

-0.06

 Từ

-0.06

wur

-0.06

 بود

-0.06

PQ

-0.06

ัวหน

-0.06

pul

-0.06

TextEdit

-0.06

POSITIVE LOGITS

หา

0.07

 Deer

0.06

ZERO

0.06

مي

0.06

estead

0.06

 skyline

0.06

 fecha

0.06

 Dental

0.06

arrings

0.06

.SC

0.06

Activations Density 0.108%

provides/allows something else

This neuron fires on service-oriented verbs that describe features or capabilities (e.g. “adds,” “provides,” “uses,” “allows,” “gives”).

No Comments

No Known Activations