INDEX

Explanations

John

np_max-act · gemini-2.0-flash

The neuron spikes specifically on the name “John” (and close variants like “Johnson”) in a list of proper names.

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

era

-0.07

 Saga

-0.07

 horribly

-0.07

Asc

-0.06

美

-0.06

 fate

-0.06

mej

-0.06

』↵↵

-0.06

POSITIVE LOGITS

John

0.14

 John

0.13

 Johnston

0.10

 JOHN

0.10

 Johnson

0.09

جان

0.09

ohn

0.09

 Johnny

0.09

Joh

0.08

 Johns

0.08

Activations Density 0.014%

John

The neuron spikes specifically on the name “John” (and close variants like “Johnson”) in a list of proper names.

No Comments

No Known Activations