INDEX

Explanations

Technical troubleshooting advice

np_max-act · gemini-2.0-flash

This neuron detects mentions of configuration options or device settings (e.g. “setting,” “settings,” “battery,” “power”).

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

 jerk

-0.07

Dataset

-0.06

 subsets

-0.06

TestData

-0.06

-find

-0.06

 полностью

-0.06

Pages

-0.06

	current

-0.06

Rai

-0.05

も

-0.05

POSITIVE LOGITS

河

0.07

DEL

0.07

 SOUND

0.07

"*"

0.07

_edge

0.06

/env

0.06

]]

0.06

 endregion

0.06

Levels

0.06

 Forward

0.06

Activations Density 0.033%

Technical troubleshooting advice

This neuron detects mentions of configuration options or device settings (e.g. “setting,” “settings,” “battery,” “power”).

No Comments

No Known Activations