INDEX

Explanations

narcissism/psychopathy

np_max-act · gemini-2.0-flash

This neuron detects references to narcissism or narcissistic personality traits or disorders.

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

 Charleston

-0.07

uddled

-0.07

_MEMBER

-0.07

 diệt

-0.06

VR

-0.06

 Dinner

-0.06

払

-0.06

 arts

-0.06

 dotted

-0.06

Yahoo

-0.06

POSITIVE LOGITS

 Symptoms

0.07

amoto

0.07

 characteristics

0.06

ص

0.06

 homelessness

0.06

.VideoCapture

0.06

.Null

0.06

=item

0.06

σιμοποι

0.06

 heuristic

0.06

Activations Density 0.004%

narcissism/psychopathy

This neuron detects references to narcissism or narcissistic personality traits or disorders.

No Comments

No Known Activations