INDEX

Explanations

Millennials/Generations

np_max-act · gemini-2.0-flash

This neuron activates on references to generational cohort names—especially “Millennials,” “Generation Y,” “Gen Y,” and similar labels.

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

 parsley

-0.07

.Keyboard

-0.07

.authorization

-0.07

-0.06

 Kensington

-0.06

openhagen

-0.06

 دانشگاه

-0.06

 numerator

-0.06

 antib

-0.06

 будинку

-0.06

POSITIVE LOGITS

 generation

0.07

Рµ

0.07

Depth

0.07

 recall

0.06

ynchron

0.06

위

0.06

_discount

0.06

自分

0.06

 generations

0.06

 культуры

0.06

Activations Density 0.003%

Millennials/Generations

This neuron activates on references to generational cohort names—especially “Millennials,” “Generation Y,” “Gen Y,” and similar labels.

No Comments

No Known Activations

Millennials/Generations

This neuron activates on references to generational cohort names—especially “Millennials,” “Generation Y,” “Gen Y,” and similar labels.

No Comments

No Known Activations