INDEX

Explanations

software development

np_max-act · gemini-2.0-flash

This neuron fires on tokens that are names of programming libraries, functions, or code identifiers (e.g. pygame, screen, size, image, color, pixel), effectively spotting snippets of code.

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

 donation

-0.07

 Yorker

-0.07

Movie

-0.07

 συνο

-0.06

ffen

-0.06

 regist

-0.06

 Justice

-0.06

 TEXT

-0.06

 Govern

-0.06

 Customer

-0.06

POSITIVE LOGITS

(quantity

0.07

 domácí

0.07

®,

0.07

={({

0.06

 envoy

0.06

ActivityResult

0.06

 Cair

0.06

_PROM

0.06

_ISR

0.06

 thừa

0.06

Activations Density 0.078%

software development

This neuron fires on tokens that are names of programming libraries, functions, or code identifiers (e.g. pygame, screen, size, image, color, pixel), effectively spotting snippets of code.

No Comments

No Known Activations

software development

This neuron fires on tokens that are names of programming libraries, functions, or code identifiers (e.g. pygame, screen, size, image, color, pixel), effectively spotting snippets of code.

No Comments

No Known Activations