INDEX

Explanations

ISO certifications

np_max-act · gemini-2.0-flash

This neuron selectively activates on numeric tokens and standard code fragments (e.g. ISO certification numbers).

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

ID

-0.07

_para

-0.07

(getActivity

-0.06

 completa

-0.06

cq

-0.06

dí

-0.06

dzi

-0.06

 Leone

-0.06

.business

-0.06

 canh

-0.06

POSITIVE LOGITS

ρας

0.07

 العن

0.06

ibling

0.06

 Adoption

0.06

Control

0.06

 boys

0.06

NET

0.06

тр

0.06

NS

0.06

VG

0.06

Activations Density 0.001%

ISO certifications

This neuron selectively activates on numeric tokens and standard code fragments (e.g. ISO certification numbers).

No Comments

No Known Activations

ISO certifications

This neuron selectively activates on numeric tokens and standard code fragments (e.g. ISO certification numbers).

No Comments

No Known Activations