INDEX

Explanations

is

np_max-act · gemini-2.0-flash

This neuron never activates on any part of the text—it 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

PLUS

-0.06

มากกว

-0.06

 Incre

-0.06

aleigh

-0.06

Tracking

-0.06

PBS

-0.06

Velocity

-0.06

Lic

-0.06

Network

-0.06

NDER

-0.06

POSITIVE LOGITS

0.07

 <!--

0.06

 subprocess

0.06

от

0.06

.getProject

0.06

섬

0.06

到了

0.06

>>::

0.06

nock

0.06

 treadmill

0.06

Activations Density 0.002%

is

This neuron never activates on any part of the text—it doesn’t detect any pattern.

No Comments

No Known Activations

is

This neuron never activates on any part of the text—it doesn’t detect any pattern.

No Comments

No Known Activations