INDEX

Explanations

medical issues

np_max-act · gemini-2.0-flash

the neuron detects text that offers advice or suggestions — sections with an instructional or imperative/supportive tone.

oai_token-act-pair · gpt-5-mini Triggered by @vetterc0

New Auto-Interp

Configuration

andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 conver

-0.07

$link

-0.06

αρα

-0.06

اري

-0.06

 suppliers

-0.06

eds

-0.06

 relevance

-0.06

 CONNECTION

-0.06

 сто

-0.06

 disciple

-0.06

POSITIVE LOGITS

icies

0.07

flamm

0.06

월

0.06

 Julio

0.06

 sparkle

0.06

usk

0.06

 Mighty

0.06

(edit

0.06

________________

0.06

 Disp

0.06

Activations Density 0.075%

medical issues

the neuron detects text that offers advice or suggestions — sections with an instructional or imperative/supportive tone.

No Comments

No Known Activations