INDEX

Explanations

white

np_max-act · gemini-2.0-flash

The neuron activates on floating-point numeric literals (decimal numbers with a fractional part).

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

ingers

-0.07

issues

-0.06

.Surface

-0.06

-em

-0.06

!"↵↵

-0.06

.which

-0.06

installation

-0.06

Н

-0.06

icerca

-0.06

_er

-0.06

POSITIVE LOGITS

ัคร

0.06

 freaking

0.06

 Nevada

0.06

 عمومی

0.06

blast

0.06

 tribe

0.06

明

0.06

tô

0.06

 createSelector

0.06

Plugin

0.06

Activations Density 0.003%

white

The neuron activates on floating-point numeric literals (decimal numbers with a fractional part).

No Comments

No Known Activations