INDEX

Explanations

doi

np_max-act · gemini-2.0-flash

The neuron activates on numeric tokens and punctuation that make up digital object identifiers (DOIs) in scholarly citations.

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

IFS

-0.06

ValueCollection

-0.06

人们

-0.06

ET

-0.06

 cycles

-0.06

rian

-0.06

Orn

-0.06

 Пр

-0.06

 Jaguar

-0.06

 Cord

-0.06

POSITIVE LOGITS

doi

0.09

doi

0.08

DOI

0.08

fecha

0.07

.decorators

0.07

anoi

0.07

productId

0.07

шиб

0.07

DOI

0.06

 diff

0.06

Activations Density 0.001%

doi

The neuron activates on numeric tokens and punctuation that make up digital object identifiers (DOIs) in scholarly citations.

No Comments

No Known Activations