INDEX

Explanations

}

np_max-act · gemini-2.0-flash

The neuron is detecting floating-point numeric literals (decimal numbers) in the 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 snapchat

-0.07

，但是

-0.07

$action

-0.07

věl

-0.06

moved

-0.06

 currentTime

-0.06

 tread

-0.06

аж

-0.06

sou

-0.06

นอ

-0.06

POSITIVE LOGITS

.getModel

0.07

.yy

0.06

\"{

0.06

 listBox

0.06

ORIZATION

0.06

.getCode

0.06

 teil

0.06

.sql

0.06

JSX

0.06

.isEmpty

0.06

Activations Density 0.029%

}

The neuron is detecting floating-point numeric literals (decimal numbers) in the text.

No Comments

No Known Activations