INDEX

Explanations

programming languages

np_max-act · gemini-2.0-flash

The neuron fires on words naming programming languages, libraries, frameworks, or other software technologies.

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

	user

-0.07

 USER

-0.07

egg

-0.07

Coords

-0.07

Entity

-0.07

 Organic

-0.06

 percussion

-0.06

DataType

-0.06

 cheapest

-0.06

Producer

-0.06

POSITIVE LOGITS

 fracking

0.07

сед

0.07

{-#

0.06

otts

0.06

childs

0.06

 OnCollision

0.06

 strokeLine

0.06

ница

0.06

游

0.06

nze

0.06

Activations Density 0.067%

programming languages

The neuron fires on words naming programming languages, libraries, frameworks, or other software technologies.

No Comments

No Known Activations