INDEX

Explanations

business or management

np_max-act · gemini-2.0-flash

This neuron activates primarily on list or section-heading terms (e.g. numbered points, bullet‐style labels, or topic headings).

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uš

-0.07

 telefon

-0.06

уш

-0.06

Uh

-0.06

요

-0.06

озя

-0.06

urry

-0.06

ente

-0.06

�

-0.06

顔

-0.06

POSITIVE LOGITS

DCALL

0.07

 mapper

0.07

Ada

0.07

"]),

0.07

UpDown

0.06

์,

0.06

)
↵
↵
↵

0.06

 Apart

0.06

 *)↵↵

0.06

pub

0.06

Activations Density 0.243%

business or management

This neuron activates primarily on list or section-heading terms (e.g. numbered points, bullet‐style labels, or topic headings).

No Comments

No Known Activations