INDEX

Explanations

role-playing game narratives

np_max-act · gemini-2.0-flash

This neuron spotlights words in the user’s imperative requests—i.e. terms framing a command or instruction (like “a,” “through,” “with,” “create,” 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 encontrado

-0.07

βο

-0.07

ováním

-0.06

[row

-0.06

レ

-0.06

apanese

-0.06

ates

-0.06

ibe

-0.06

/compiler

-0.06

 Shane

-0.06

POSITIVE LOGITS

 simulations

0.06

 Assign

0.06

лит

0.06

動

0.06

 vypad

0.06

Listening

0.06

iembre

0.06

Sy

0.06

 kabul

0.06

Activations Density 0.023%

role-playing game narratives

This neuron spotlights words in the user’s imperative requests—i.e. terms framing a command or instruction (like “a,” “through,” “with,” “create,” etc.)

No Comments

No Known Activations

role-playing game narratives

This neuron spotlights words in the user’s imperative requests—i.e. terms framing a command or instruction (like “a,” “through,” “with,” “create,” etc.)

No Comments

No Known Activations