INDEX

Explanations

code symbols

np_max-act · gemini-2.0-flash

The neuron primarily detects floating‐point numeric literals (decimal numbers) in the 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

 viruses

-0.07

_duplicates

-0.07

 багать

-0.07

 UIFont

-0.07

(baseUrl

-0.07

 Holocaust

-0.06

azon

-0.06

 асп

-0.06

列

-0.06

 Adoption

-0.06

POSITIVE LOGITS

.getImage

0.07

 datové

0.07

ζα

0.06

Kb

0.06

 sentiment

0.06

년

0.06

 Federal

0.06

디어

0.06

ũi

0.06

Blocks

0.06

Activations Density 0.035%

code symbols

The neuron primarily detects floating‐point numeric literals (decimal numbers) in the code.

No Comments

No Known Activations