INDEX

Explanations

you

np_max-act · gemini-2.0-flash

The neuron detects occurrences of the personal pronouns “you” (and to a lesser extent “I”), especially when they appear in user identity or role–question contexts.

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

�

-0.07

관

-0.07

Decimal

-0.07

\Facades

-0.06

TO

-0.06

كر

-0.06

 Brah

-0.06

_oauth

-0.06

to

-0.06

 раньше

-0.06

POSITIVE LOGITS

ycle

0.07

WebService

0.06

jong

0.06

oling

0.06

_ix

0.06

 alternative

0.06

rtle

0.06

omething

0.06

oley

0.06

 Modi

0.06

Activations Density 0.006%

you

The neuron detects occurrences of the personal pronouns “you” (and to a lesser extent “I”), especially when they appear in user identity or role–question contexts.

No Comments

No Known Activations

you

The neuron detects occurrences of the personal pronouns “you” (and to a lesser extent “I”), especially when they appear in user identity or role–question contexts.

No Comments

No Known Activations