INDEX

Explanations

Game abilities

np_max-act · gemini-2.0-flash

This neuron detects mentions of video-game ability and skill terms (e.g. “Skill,” “Ultimate,” “Passive,” names of abilities, related stats).

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Stan

-0.07

 Kromě

-0.07

recipient

-0.07

Opr

-0.06

 Tanks

-0.06

 گر

-0.06

 July

-0.06

_lot

-0.06

nic

-0.06

POSITIVE LOGITS

company

0.08

	comment

0.06

 растений

0.06

 belongings

0.06

[+

0.06

реди

0.06

HDC

0.06

 Durant

0.06

회사

0.06

 المدينة

0.06

Activations Density 0.007%

Game abilities

This neuron detects mentions of video-game ability and skill terms (e.g. “Skill,” “Ultimate,” “Passive,” names of abilities, related stats).

No Comments

No Known Activations