INDEX

Explanations

period

np_max-act · gemini-2.0-flash

The neuron activates on patent citation strings (e.g. “U.S. Pat. No. 4,xxx,xxx”).

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

.replace

-0.07

Annotations

-0.07

Date

-0.07

 licences

-0.06

 reminds

-0.06

カード

-0.06

 impressions

-0.06

 licenses

-0.06

XYZ

-0.06

 runApp

-0.06

POSITIVE LOGITS

.jsx

0.07

mo

0.06

=S

0.06

 vliv

0.06

株式会社

0.06

 شمال

0.06

 طب

0.06

 bully

0.06

 розк

0.06

虫

0.06

Activations Density 0.003%

period

The neuron activates on patent citation strings (e.g. “U.S. Pat. No. 4,xxx,xxx”).

No Comments

No Known Activations