INDEX

Explanations

code and comparisons

np_max-act · gemini-2.0-flash

This neuron primarily detects the literal numeral “0.”

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

 نی

-0.07

út

-0.07

finalize

-0.07

-forward

-0.07

ुण

-0.06

 Neighbor

-0.06

یف

-0.06

 قاب

-0.06

 Timer

-0.06

度

-0.06

POSITIVE LOGITS

�

0.07

0.06

-roll

0.06

|R

0.06

 लगभग

0.06

 Internet

0.06

 libr

0.06

_when

0.06

/pass

0.06

Mathf

0.06

Activations Density 0.046%

code and comparisons

This neuron primarily detects the literal numeral “0.”

No Comments

No Known Activations