INDEX

Explanations

punctuation

np_max-act · gemini-2.0-flash

The neuron fires on numeric literal tokens (e.g. integers or decimals) in code or templates.

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

Lines

-0.07

Yuk

-0.07

 Promise

-0.07

_yes

-0.07

posable

-0.07

{:

-0.06

,message

-0.06

^{

-0.06

：↵

-0.06

replace

-0.06

POSITIVE LOGITS

 Monitor

0.08

0.07

.EXTRA

0.06

_self

0.06

갤

0.06

itness

0.06

 subscript

0.06

บาง

0.06

Trader

0.06

Activations Density 0.055%

punctuation

The neuron fires on numeric literal tokens (e.g. integers or decimals) in code or templates.

No Comments

No Known Activations