INDEX

Explanations

honor

np_max-act · gemini-2.0-flash

This neuron activates on occurrences of “honor” (and its variant “honour”).

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

achine

-0.07

Lake

-0.07

áč

-0.07

 davidjl

-0.07

 Goose

-0.07

askell

-0.06

Cat

-0.06

 Alice

-0.06

 розповід

-0.06

 plates

-0.06

POSITIVE LOGITS

 honor

0.17

 Honor

0.15

 honour

0.15

 honored

0.14

Hon

0.13

 honoured

0.13

 honorable

0.12

 honors

0.12

 honoring

0.11

 Honour

0.11

Activations Density 0.009%

honor

This neuron activates on occurrences of “honor” (and its variant “honour”).

No Comments

No Known Activations