INDEX

Explanations

archetypes

np_max-act · gemini-2.0-flash

This neuron detects mentions of Jung‐style concepts—especially “archetype”/“archetypal” and “collective unconscious.”

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

))))

-0.07

RowAnimation

-0.07

 Speaking

-0.06

 Elliot

-0.06

mobx

-0.06

Fizz

-0.06

 Lori

-0.06

 Nicole

-0.06

%B

-0.06

gettext

-0.06

POSITIVE LOGITS

 archetype

0.08

 demanded

0.07

 эконом

0.07

și

0.06

('>

0.06

 recorded

0.06

Gateway

0.06

(anchor

0.06

,y

0.06

ined

0.06

Activations Density 0.004%

archetypes

This neuron detects mentions of Jung‐style concepts—especially “archetype”/“archetypal” and “collective unconscious.”

No Comments

No Known Activations