INDEX

Explanations

Inventions

np_max-act · gemini-2.0-flash

This neuron fires on document tokens that are numeric references or measurements (e.g. part numbers, figure numbers, dimensions).

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

“At

-0.07

 turnaround

-0.07

transactions

-0.07

_pl

-0.07

 Debbie

-0.07

IMENT

-0.06

ario

-0.06

 Fakültesi

-0.06

 conce

-0.06

.addNode

-0.06

POSITIVE LOGITS

 اد

0.07

坛

0.06

LENGTH

0.06

천

0.06

Projected

0.06

 путем

0.06

 lettre

0.06

 ημέ

0.06

ลล

0.06

 بور

0.06

Activations Density 0.013%

Inventions

This neuron fires on document tokens that are numeric references or measurements (e.g. part numbers, figure numbers, dimensions).

No Comments

No Known Activations