INDEX

Explanations

SS

np_max-act · gemini-2.0-flash

The neuron detects U.S. Navy ship designations, firing on mentions of “USS” (and similar vessel prefixes) in the text.

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

yen

-0.08

Cơ

-0.07

GINE

-0.07

oyo

-0.07

Phone

-0.07

sexo

-0.07

_yellow

-0.07

 děti

-0.06

SIG

-0.06

POSITIVE LOGITS

USS

0.09

уст

0.07

/place

0.07

>{{$

0.07

HMS

0.06

 통합

0.06

.launch

0.06

 seamlessly

0.06

］

0.06

 undefeated

0.06

Activations Density 0.002%

SS

The neuron detects U.S. Navy ship designations, firing on mentions of “USS” (and similar vessel prefixes) in the text.

No Comments

No Known Activations

SS

The neuron detects U.S. Navy ship designations, firing on mentions of “USS” (and similar vessel prefixes) in the text.

No Comments

No Known Activations