INDEX

Explanations

medical history

np_max-act · gemini-2.0-flash

This neuron detects section-heading labels (e.g., “SUBJECTIVE:”, “OBJECTIVE:”, “MEDICATIONS:”, “ALLERGIES:”, “ASSESSMENT:”, “PLAN:”) in a clinical note.

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

 vibrations

-0.07

entrant

-0.07

markdown

-0.07

GAME

-0.07

厂

-0.07

 آبی

-0.06

 executives

-0.06

 během

-0.06

 české

-0.06

ufreq

-0.06

POSITIVE LOGITS

ahoma

0.06

 Squad

0.06

 userDao

0.06

PSU

0.06

-born

0.06

beth

0.06

 Jude

0.06

uya

0.06

 предмет

0.05

ived

0.05

Activations Density 0.008%

medical history

This neuron detects section-heading labels (e.g., “SUBJECTIVE:”, “OBJECTIVE:”, “MEDICATIONS:”, “ALLERGIES:”, “ASSESSMENT:”, “PLAN:”) in a clinical note.

No Comments

No Known Activations