INDEX

Explanations

Alexander

np_max-act · gemini-2.0-flash

This neuron detects occurrences of the proper name “Alexander.”

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

 probability

-0.07

 calories

-0.07

 Service

-0.07

.up

-0.07

up

-0.07

回

-0.07

その

-0.06

up

-0.06

uf

-0.06

POSITIVE LOGITS

 Mitchell

0.09

 Jordan

0.09

 Alexander

0.09

Mitch

0.09

Nick

0.09

 Nickel

0.09

Alexander

0.09

 Sasha

0.09

 McMahon

0.09

 Nick

0.08

Activations Density 0.042%

Alexander

This neuron detects occurrences of the proper name “Alexander.”

No Comments

No Known Activations