INDEX

Explanations

disasters and accidents

np_max-act · gemini-2.0-flash

The neuron is primarily activated by named entities—especially geographic place names and other proper nouns.

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

 pigeon

-0.07

-0.06

agh

-0.06

ียง

-0.06

กำ

-0.06

vol

-0.06

рам

-0.06

านคร

-0.06

 الخط

-0.06

 Sanat

-0.06

POSITIVE LOGITS

 agricultural

0.07

.gf

0.06

 struggles

0.06

 attempts

0.06

 Rights

0.06

 Victory

0.06

....

0.06

無し

0.06

 situaci

0.06

 FULL

0.06

Activations Density 0.018%

disasters and accidents

The neuron is primarily activated by named entities—especially geographic place names and other proper nouns.

No Comments

No Known Activations