INDEX

Explanations

disturbance

np_max-act · gemini-2.0-flash

The neuron activates on terms denoting emotional or psychological disturbance (e.g. disturbed, distressed, unsettled, upset).

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

 qreal

-0.06

 Index

-0.06

 QIcon

-0.06

 Paige

-0.06

Best

-0.06

 picks

-0.06

 profiles

-0.06

avn

-0.06

 Reid

-0.06

POSITIVE LOGITS

 disturb

0.13

 disturbed

0.13

 disturbance

0.11

 disturbing

0.09

 disturbances

0.09

 distur

0.09

�

0.08

0.07

 dwelling

0.07

 Dennis

0.07

Activations Density 0.007%

disturbance

The neuron activates on terms denoting emotional or psychological disturbance (e.g. disturbed, distressed, unsettled, upset).

No Comments

No Known Activations