INDEX

Explanations

emerg

np_max-act · gemini-2.0-flash

The neuron activates on terminology from complex‐systems theory—words like “complex,” “systems,” “emergent,” “behavior,” and “interactions.”

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

νή

-0.06

-arrow

-0.06

WX

-0.06

Nh

-0.06

 heeft

-0.06

antino

-0.06

isory

-0.06

šetř

-0.06

γορ

-0.06

POSITIVE LOGITS

 Sudan

0.07

 yelling

0.06

 timid

0.06

unter

0.06

 incapable

0.06

帰

0.06

 يق

0.06

 تط

0.06

(query

0.06

 Комп

0.06

Activations Density 0.011%

emerg

The neuron activates on terminology from complex‐systems theory—words like “complex,” “systems,” “emergent,” “behavior,” and “interactions.”

No Comments

No Known Activations