INDEX

Explanations

fun

np_max-act · gemini-2.0-flash

The neuron fires on promotional descriptors—especially adjectives and adverbs—emphasizing fun, engaging, interactive, or educational qualities.

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

-0.06

Mayor

-0.06

Van

-0.06

prom

-0.06

१९

-0.06

Instruction

-0.06

 obvious

-0.06

告诉

-0.06

 Ар

-0.06

tie

-0.06

POSITIVE LOGITS

redit

0.08

 UserModel

0.06

ляються

0.06

 podob

0.06

setProperty

0.06

 jose

0.06

 relação

0.06

/community

0.06

availability

0.06

urpose

0.06

Activations Density 0.061%

fun

The neuron fires on promotional descriptors—especially adjectives and adverbs—emphasizing fun, engaging, interactive, or educational qualities.

No Comments

No Known Activations