INDEX

Explanations

initial

np_max-act · gemini-2.0-flash

The neuron strongly activates on the numeric value assigned to the “initial‐scale” parameter in viewport meta tags.

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

ihad

-0.06

Gum

-0.06

amate

-0.06

etim

-0.06

bay

-0.06

 kter

-0.06

.TimeUnit

-0.06

WAV

-0.06

dmg

-0.06

Legend

-0.06

POSITIVE LOGITS

(Render

0.07

 compassionate

0.07

ubectl

0.07

 tabletop

0.07

 deployments

0.06

슬

0.06

 laboratory

0.06

 beforeEach

0.06

opup

0.06

 başk

0.06

Activations Density 0.001%

initial

The neuron strongly activates on the numeric value assigned to the “initial‐scale” parameter in viewport meta tags.

No Comments

No Known Activations