INDEX

Explanations

:

np_max-act · gemini-2.0-flash

The neuron flags floating‐point number tokens (i.e. numeric literals with decimals).

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

bread

-0.07

 Argentina

-0.07

.selectAll

-0.06

 mentors

-0.06

.ForegroundColor

-0.06

enc

-0.06

/ion

-0.06

christ

-0.06

 fruity

-0.06

 dispensaries

-0.06

POSITIVE LOGITS

九

0.07

'ét

0.07

алося

0.06

cé

0.06

 висок

0.06

atie

0.06

域

0.06

QUENCY

0.06

 Eğitim

0.06

udp

0.06

Activations Density 0.030%

:

The neuron flags floating‐point number tokens (i.e. numeric literals with decimals).

No Comments

No Known Activations