INDEX

Explanations

life

np_max-act · gemini-2.0-flash

This neuron responds to mentions of one’s personal life span or experience—especially tokens in phrases like “my life,” “whole life,” and similar autobiographical references.

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

 okay

-0.07

 terse

-0.07

Trees

-0.06

 sorunu

-0.06

 PlayStation

-0.06

_router

-0.06

Kre

-0.06

 meals

-0.06

 congestion

-0.06

 Pers

-0.06

POSITIVE LOGITS

 lifelong

0.07

tiv

0.07

 LIFE

0.07

 Sting

0.06

тє

0.06

SSC

0.06

>/<

0.06

atural

0.06

.setString

0.06

ESC

0.06

Activations Density 0.019%

life

This neuron responds to mentions of one’s personal life span or experience—especially tokens in phrases like “my life,” “whole life,” and similar autobiographical references.

No Comments

No Known Activations