INDEX

Explanations

marketing

np_max-act · gemini-2.0-flash

The neuron fires on marketing‐ and sales‐related terms (e.g. words about selling, flavors, promotion, and marketing).

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

arp

-0.08

 vague

-0.06

AMA

-0.06

 Grow

-0.06

_traffic

-0.06

tre

-0.06

alar

-0.06

ует

-0.06

 Play

-0.06

 Game

-0.06

POSITIVE LOGITS

Datum

0.07

%X

0.06

_Date

0.06

شتر

0.06

scriptId

0.06

errated

0.06

_marshall

0.06

 konut

0.06

개를

0.06

	iNdEx

0.06

Activations Density 0.013%

marketing

The neuron fires on marketing‐ and sales‐related terms (e.g. words about selling, flavors, promotion, and marketing).

No Comments

No Known Activations