INDEX

Explanations

size/count

np_max-act · gemini-2.0-flash

The neuron fires on 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

UpInside

-0.08

_receive

-0.07

ゲ

-0.06

index

-0.06

Scan

-0.06

 hell

-0.06

 Levels

-0.06

 Gavin

-0.06

	store

-0.06

ул

-0.06

POSITIVE LOGITS

 riches

0.07

 Cosby

0.06

��

0.06

 Wohn

0.06

EVP

0.06

Msp

0.06

CHP

0.06

.getInput

0.06

 finer

0.06

indre

0.06

Activations Density 0.010%

size/count

The neuron fires on floating‐point numeric literals (decimal numbers) in the code.

No Comments

No Known Activations