INDEX

Explanations

numbers

np_max-act · gemini-2.0-flash

This neuron detects numeric literal tokens (e.g. integer constants specifying sizes or values) in code.

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

 مهد

-0.09

 Для

-0.07

δί

-0.07

ढ़

-0.07

 Giám

-0.07

 خواهند

-0.06

믿

-0.06

 msgs

-0.06

mqtt

-0.06

 irrational

-0.06

POSITIVE LOGITS

 startDate

0.07

-org

0.06

.Atomic

0.06

?<

0.06

 theatrical

0.06

 parks

0.06

.local

0.06

 dashed

0.06

quivo

0.06

/master

0.06

Activations Density 0.010%

numbers

This neuron detects numeric literal tokens (e.g. integer constants specifying sizes or values) in code.

No Comments

No Known Activations

numbers

This neuron detects numeric literal tokens (e.g. integer constants specifying sizes or values) in code.

No Comments

No Known Activations