INDEX

Explanations

display technology

np_max-act · gemini-2.0-flash

This neuron responds to sentence-initial discourse markers or connective words (e.g. “In,” “Thus,” “The,” “Compared,” “Recently,” etc.) that structure and transition between sections of technical text.

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

 twilight

-0.07

 مبت

-0.06

ंद

-0.06

，没有

-0.06

={`${

-0.06

pcb

-0.06

lightbox

-0.06

armac

-0.06

 αδ

-0.06

 هنوز

-0.06

POSITIVE LOGITS

 tả

0.07

APON

0.06

 засобів

0.06

 stationed

0.06

 vinyl

0.06

ey

0.06

ago

0.06

 rigor

0.06

盘

0.06

 الأولى

0.06

Activations Density 0.055%

display technology

This neuron responds to sentence-initial discourse markers or connective words (e.g. “In,” “Thus,” “The,” “Compared,” “Recently,” etc.) that structure and transition between sections of technical text.

No Comments

No Known Activations

display technology

This neuron responds to sentence-initial discourse markers or connective words (e.g. “In,” “Thus,” “The,” “Compared,” “Recently,” etc.) that structure and transition between sections of technical text.

No Comments

No Known Activations