INDEX

Explanations

unusual names/words

np_max-act · gemini-2.0-flash

The neuron responds to capitalized proper names—place names, band or artist names, and personal names.

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

-0.08

 clusters

-0.07

.Cl

-0.06

 Champions

-0.06

 cluster

-0.06

 images

-0.06

 모델

-0.06

 submits

-0.06

POSITIVE LOGITS

ard

0.11

arg

0.10

ARG

0.10

ert

0.10

orne

0.10

erge

0.10

arp

0.10

 Gerard

0.10

ARP

0.09

urd

0.09

Activations Density 0.532%

unusual names/words

The neuron responds to capitalized proper names—place names, band or artist names, and personal names.

No Comments

No Known Activations