INDEX

Explanations

festivals

np_max-act · gemini-2.0-flash

This neuron activates on the names of festivals (e.g. Holi, Diwali, Pongal) and related festival terms.

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

 MATERIAL

-0.07

.contentMode

-0.07

Decision

-0.07

ريف

-0.06

 dall

-0.06

 ministries

-0.06

 گردد

-0.06

otland

-0.06

setChecked

-0.06

 fetal

-0.06

POSITIVE LOGITS

 Econom

0.07

-quarter

0.06

-exp

0.06

Ki

0.06

mb

0.06

 financially

0.06

-over

0.06

แชม

0.06

 experi

0.06

फ

0.06

Activations Density 0.032%

festivals

This neuron activates on the names of festivals (e.g. Holi, Diwali, Pongal) and related festival terms.

No Comments

No Known Activations