INDEX

Explanations

at

np_max-act · gemini-2.0-flash

This neuron detects tokens in category lines that list athletes “at the [year] [event]” (e.g. “volleyball players at the 2016 Summer Olympics”), i.e. mentions of participation in specific sporting events.

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

 Installed

-0.06

 Viện

-0.06

 तथ

-0.06

 welt

-0.06

ratulations

-0.06

 ApiService

-0.06

If

-0.06

Af

-0.06

 Cher

-0.05

��

-0.05

POSITIVE LOGITS

.animation

0.07

 alignment

0.06

 мет

0.06

()."

0.06

skills

0.06

되는

0.06

ordum

0.06

artic

0.06

énom

0.06

LEFT

0.06

Activations Density 0.002%

at

This neuron detects tokens in category lines that list athletes “at the [year] [event]” (e.g. “volleyball players at the 2016 Summer Olympics”), i.e. mentions of participation in specific sporting events.

No Comments

No Known Activations

at

This neuron detects tokens in category lines that list athletes “at the [year] [event]” (e.g. “volleyball players at the 2016 Summer Olympics”), i.e. mentions of participation in specific sporting events.

No Comments

No Known Activations