INDEX

Explanations

201

np_max-act · gemini-2.0-flash

The neuron activates on four‐digit year tokens (e.g. “2015,” “2010,” “2016,” “2012,” etc.).

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

 Gale

-0.07

ENG

-0.07

 statistical

-0.07

 fung

-0.06

eng

-0.06

erra

-0.06

 Rick

-0.06

 corn

-0.06

 Cake

-0.06

 Luck

-0.06

POSITIVE LOGITS

AMS

0.07

 єв

0.07

Mission

0.07

hips

0.07

 recounts

0.06

 layoutManager

0.06

ufac

0.06

 ************************

0.06

SETTINGS

0.06

force

0.06

Activations Density 0.003%

201

The neuron activates on four‐digit year tokens (e.g. “2015,” “2010,” “2016,” “2012,” etc.).

No Comments

No Known Activations