INDEX

Explanations

*/

np_max-act · gemini-2.0-flash

The neuron detects floating‐point numeric literals (i.e. tokens containing a decimal point and digits).

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

consult

-0.07

 frame

-0.07

ictures

-0.07

trans

-0.07

end

-0.06

andalone

-0.06

elerle

-0.06

Answers

-0.06

.getDouble

-0.06

 rules

-0.06

POSITIVE LOGITS

Ố

0.07

 Сред

0.07

 خرد

0.07

 spontaneously

0.06

อก

0.06

 Liste

0.06

深

0.06

深

0.06

 revenge

0.06

 Cougar

0.06

Activations Density 0.004%

*/

The neuron detects floating‐point numeric literals (i.e. tokens containing a decimal point and digits).

No Comments

No Known Activations