INDEX

Explanations

Citations

np_max-act · gemini-2.0-flash

The main thing this neuron does is detect academic citation markers—author names, years, and reference brackets in scholarly 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.07

 symbols

-0.06

”↵

-0.06

 fluent

-0.06

 also

-0.06

 comun

-0.06

 poorer

-0.06

_WRONLY

-0.06

Unicode

-0.06

gc

-0.06

POSITIVE LOGITS

 Kirst

0.07

+]

0.07

 Binder

0.07

no

0.06

 }>↵

0.06

Vin

0.06

   ↵↵

0.06

 город

0.06

percentage

0.06

Activations Density 0.025%

Citations

The main thing this neuron does is detect academic citation markers—author names, years, and reference brackets in scholarly text.

No Comments

No Known Activations