INDEX

Explanations

family and relationships

np_max-act · gemini-2.0-flash

This neuron activates on mentions of family relationships or family members.

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

 lugar

-0.07

 contagious

-0.07

 Leigh

-0.06

 داشت

-0.06

迷

-0.06

(cps

-0.06

 دوم

-0.06

Hp

-0.06

InputBorder

-0.06

 café

-0.06

POSITIVE LOGITS

----------------

0.07

.Main

0.06

Broad

0.06

Exact

0.06

stellar

0.06

-global

0.06

htmlspecialchars

0.06

_Return

0.06

NIC

0.06

roadcast

0.06

Activations Density 0.060%

family and relationships

This neuron activates on mentions of family relationships or family members.

No Comments

No Known Activations