INDEX

Explanations

density

np_max-act · gemini-2.0-flash

This neuron detects mentions of lipoprotein cholesterol subfractions—specifically phrases like “low-density,” “high-density,” or “non-high-density” when describing lipid measurements.

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

 Mercedes

-0.06

 doprav

-0.06

 concludes

-0.06

.ButterKnife

-0.06

 bikes

-0.06

 pies

-0.06

 Bear

-0.06

 wannonce

-0.06

.Remove

-0.06

 embryos

-0.06

POSITIVE LOGITS

↵

0.07

 wäh

0.07

/DTD

0.07

؟↵

0.06

۲۵

0.06

лит

0.06

 tandem

0.06

 выяв

0.06

_File

0.06

 }↵↵↵↵

0.06

Activations Density 0.001%

density

This neuron detects mentions of lipoprotein cholesterol subfractions—specifically phrases like “low-density,” “high-density,” or “non-high-density” when describing lipid measurements.

No Comments

No Known Activations