INDEX

Explanations

Legal documents

np_max-act · gemini-2.0-flash

This neuron detects references to testing or analytic equipment (e.g., machines, operators, malfunctions) and related technical terms.

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

 Leah

-0.07

bounded

-0.07

 angles

-0.07

 Statement

-0.07

 regret

-0.06

.reward

-0.06

handlers

-0.06

_format

-0.06

网

-0.06

POSITIVE LOGITS

 ajout

0.07

 modified

0.06

ekkür

0.06

altimore

0.06

 seminal

0.06

टक

0.06

 Adidas

0.06

Mov

0.06

 composer

0.06

Designed

0.06

Activations Density 0.007%

Legal documents

This neuron detects references to testing or analytic equipment (e.g., machines, operators, malfunctions) and related technical terms.

No Comments

No Known Activations