INDEX

Explanations

artillery

np_max-act · gemini-2.0-flash

The neuron fires on mentions of artillery weaponry (e.g., “artillery,” “gun,” “field gun,” 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

 approves

-0.06

 employees

-0.06

dex

-0.06

 Temperature

-0.06

 Beatles

-0.06

 Sheep

-0.06

奇

-0.06

 Virus

-0.06

 depressed

-0.06

 train

-0.06

POSITIVE LOGITS

_cli

0.07

 průběhu

0.07

 fireworks

0.07

 annihil

0.07

砲

0.07

 Honour

0.06

 یا

0.06

ebin

0.06

Put

0.06

?(

0.06

Activations Density 0.007%

artillery

The neuron fires on mentions of artillery weaponry (e.g., “artillery,” “gun,” “field gun,” etc.).

No Comments

No Known Activations

artillery

The neuron fires on mentions of artillery weaponry (e.g., “artillery,” “gun,” “field gun,” etc.).

No Comments

No Known Activations