INDEX

Explanations

police

np_max-act · gemini-2.0-flash

The neuron activates on instances of the word “police” (in any casing).

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

 Harmon

-0.08

-0.07

or

-0.06

 Original

-0.06

stringstream

-0.06

Rom

-0.06

 Karn

-0.06

Fil

-0.06

POSITIVE LOGITS

 police

0.17

 Police

0.16

Police

0.14

 policemen

0.09

警

0.08

 lights

0.08

Authorities

0.08

 arrests

0.08

 parliamentary

0.08

 Polic

0.08

Activations Density 0.011%

police

The neuron activates on instances of the word “police” (in any casing).

No Comments

No Known Activations