INDEX

Explanations

Police shootings

np_max-act · gemini-2.0-flash

The neuron fires on descriptive adjectives or phrases that characterize a suspect’s status or threat (e.g. “unarmed,” “naked,” “knife-wielding”).

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

vap

-0.06

ผล

-0.06

 PARTIC

-0.06

 convolution

-0.06

Don

-0.06

.Channel

-0.06

atology

-0.06

WM

-0.06

손

-0.06

gr

-0.06

POSITIVE LOGITS

0.07

_eff

0.07

 фіз

0.06

pdo

0.06

 CheckBox

0.06

=&

0.06

 Scientists

0.06

 وز

0.06

زا

0.06

приєм

0.06

Activations Density 0.023%

Police shootings

The neuron fires on descriptive adjectives or phrases that characterize a suspect’s status or threat (e.g. “unarmed,” “naked,” “knife-wielding”).

No Comments

No Known Activations