INDEX

Explanations

year

np_max-act · gemini-2.0-flash

The neuron selectively activates on numeric age/category labels (e.g. the “19” in “Under‐19” or “21” in “Under‐21”), i.e. youth‐level age designations.

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

flash

-0.07

Meg

-0.07

 ülkenin

-0.06

 Kaiser

-0.06

 cork

-0.06

Gün

-0.06

relude

-0.06

通過

-0.06

 Lloyd

-0.06

خذ

-0.06

POSITIVE LOGITS

ASI

0.07

asi

0.06

 playlist

0.06

�

0.06

plotlib

0.06

 exploring

0.06

─

0.06

.Entities

0.06

.figure

0.06

/kubernetes

0.06

Activations Density 0.002%

year

The neuron selectively activates on numeric age/category labels (e.g. the “19” in “Under‐19” or “21” in “Under‐21”), i.e. youth‐level age designations.

No Comments

No Known Activations