INDEX

Explanations

circular movement

np_max-act · gemini-2.0-flash

The neuron fires on imperative, instructional language—particularly verbs and cues that introduce or guide step-by-step directions.

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

ember

-0.07

 Assertions

-0.06

padding

-0.06

(className

-0.06

bru

-0.06

 Usuario

-0.06

amura

-0.06

ีอ

-0.06

Zap

-0.06

یشن

-0.06

POSITIVE LOGITS

中

0.08

 Chill

0.07

 Spears

0.07

_UNITS

0.06

 Intelli

0.06

silent

0.06

Good

0.06

KC

0.06

_configs

0.06

状況

0.06

Activations Density 0.021%

circular movement

The neuron fires on imperative, instructional language—particularly verbs and cues that introduce or guide step-by-step directions.

No Comments

No Known Activations