INDEX

Explanations

rather

np_max-act · gemini-2.0-flash

This neuron does not consistently activate on any content—it remains effectively inactive and does not detect a particular pattern.

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

-0.07

noop

-0.07

온

-0.07

urança

-0.07

adena

-0.07

discord

-0.06

 Tribune

-0.06

Mob

-0.06

Jou

-0.06

POSITIVE LOGITS

-of

0.07

.addRow

0.07

 않고

0.07

querySelector

0.07

 hvis

0.06

ักก

0.06

ุคคล

0.06

ующ

0.06

 richt

0.06

.IsTrue

0.06

Activations Density 0.009%

rather

This neuron does not consistently activate on any content—it remains effectively inactive and does not detect a particular pattern.

No Comments

No Known Activations