INDEX

Explanations

sound

np_max-act · gemini-2.0-flash

The neuron fires on occurrences of “sound”-related terms—particularly “infrasound” and other low-frequency or noise/sound vocabulary.

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

 Parliamentary

-0.06

 onemoc

-0.06

ρή

-0.06

 FIXME

-0.06

sep

-0.06

ेयर

-0.06

("%.

-0.06

itioner

-0.06

 پاد

-0.06

Abstract

-0.06

POSITIVE LOGITS

 neger

0.07

ليم

0.07

0.06

 dryer

0.06

 sound

0.06

�

0.06

/popper

0.06

:message

0.06

_create

0.06

들

0.06

Activations Density 0.012%

sound

The neuron fires on occurrences of “sound”-related terms—particularly “infrasound” and other low-frequency or noise/sound vocabulary.

No Comments

No Known Activations