INDEX

Explanations

pain

np_max-act · gemini-2.0-flash

The neuron fires on mentions of pain‐relief medications and related terms (e.g. “pain,” “relief,” “acetaminophen,” “ibuprofen,” “Tylenol,” 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

tax

-0.07

зд

-0.07

 свойства

-0.07

tag

-0.06

oke

-0.06

_tD

-0.06

φή

-0.06

andas

-0.06

 Communist

-0.06

 testName

-0.06

POSITIVE LOGITS

介

0.07

 pain

0.06

 Pain

0.06

 контра

0.06

 ninth

0.06

/menu

0.06

우

0.06

 Elevated

0.06

 scrolled

0.06

jury

0.06

Activations Density 0.003%

pain

The neuron fires on mentions of pain‐relief medications and related terms (e.g. “pain,” “relief,” “acetaminophen,” “ibuprofen,” “Tylenol,” etc.).

No Comments

No Known Activations