INDEX

Explanations

Family

np_max-act · gemini-2.0-flash

This neuron activates on occurrences of the word “family” (and its close variants).

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Norton

-0.07

 обнаруж

-0.07

 kromě

-0.07

.Check

-0.07

 overt

-0.06

----↵↵

-0.06

 vượt

-0.06

 lecturer

-0.06

 вред

-0.06

 Toastr

-0.06

POSITIVE LOGITS

 family

0.18

 Family

0.17

 families

0.15

family

0.14

Family

0.14

 FAMILY

0.13

 Families

0.12

-family

0.09

 clan

0.08

ANY

0.08

Activations Density 0.033%

Family

This neuron activates on occurrences of the word “family” (and its close variants).

No Comments

No Known Activations