INDEX

Explanations

C

np_max-act · gemini-2.0-flash

The neuron detects mentions of the C# language name (the “C#” token) in the text.

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

"To

-0.07

.Sm

-0.07

초

-0.07

ぬ

-0.07

网

-0.06

슈

-0.06

 rempl

-0.06

 önüne

-0.06

缩

-0.06

laden

-0.06

POSITIVE LOGITS

 güneş

0.07

 ObservableCollection

0.07

gıç

0.07

ImageContext

0.07

.spacing

0.07

 Fiat

0.06

 HttpHeaders

0.06

Looking

0.06

cal

0.06

 differed

0.06

Activations Density 0.012%

C

The neuron detects mentions of the C# language name (the “C#” token) in the text.

No Comments

No Known Activations