INDEX

Explanations

awards and honors

np_max-act · gemini-2.0-flash

This neuron fires on the “For … to …” honor‐citation phrases that give the reason for an award (e.g. “For services to medicine”).

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

(ent

-0.07

otypical

-0.07

 annum

-0.06

outube

-0.06

 gathers

-0.06

Since

-0.06

 베스트

-0.06

Animations

-0.06

ContentAlignment

-0.06

 kits

-0.06

POSITIVE LOGITS

抬

0.06

_ec

0.06

 Telecom

0.06

 automát

0.06

 funcs

0.06

 conosc

0.06

 UIBar

0.06

ปฏ

0.05

šetření

0.05

ayd

0.05

Activations Density 0.037%

awards and honors

This neuron fires on the “For … to …” honor‐citation phrases that give the reason for an award (e.g. “For services to medicine”).

No Comments

No Known Activations