INDEX

Explanations

Names, locations, abbreviations

np_max-act · gemini-2.0-flash

The neuron selectively activates on the Italian phrase “Intelligenza Artificiale” (and its subparts), i.e. references to artificial intelligence.

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

 proved

-0.07

DEST

-0.07

 seems

-0.07

#pragma

-0.07

_device

-0.07

 pony

-0.06

 implementation

-0.06

 crawling

-0.06

 implementations

-0.06

έντ

-0.06

POSITIVE LOGITS

 yemek

0.07

 результате

0.06

 rollers

0.06

 cigaret

0.06

è

0.06

�

0.06

awaiter

0.06

allel

0.06

 august

0.06

SEL

0.06

Activations Density 0.021%

Names, locations, abbreviations

The neuron selectively activates on the Italian phrase “Intelligenza Artificiale” (and its subparts), i.e. references to artificial intelligence.

No Comments

No Known Activations