INDEX

Explanations

}

np_max-act · gemini-2.0-flash

The neuron never activates on any of the shown tokens—it’s effectively a “dead” neuron that doesn’t detect any 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 маль

-0.07

Material

-0.06

elter

-0.06

 interfer

-0.06

Admin

-0.06

forget

-0.06

lingen

-0.06

ebra

-0.06

งใน

-0.06

POSITIVE LOGITS

 perfected

0.07

angler

0.07

 अपन

0.07

 klik

0.07

=""><

0.07

_REFERER

0.06

.keyCode

0.06

 CharSet

0.06

 захворювання

0.06

.ACT

0.06

Activations Density 0.053%

}

The neuron never activates on any of the shown tokens—it’s effectively a “dead” neuron that doesn’t detect any pattern.

No Comments

No Known Activations