INDEX

Explanations

references to cleaning products or their applications

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

inspace

-0.15

å¹ķ

-0.14

agina

-0.14

QM

-0.14

ÐµÑĢÐ°Ð¼Ð¸

-0.14

alendar

-0.14

.crm

-0.14

 kháº©u

-0.13

Sortable

-0.13

_charset

-0.13

POSITIVE LOGITS

 penetrating

0.27

oil

0.26

wax

0.25

Wax

0.24

 oils

0.24

Oil

0.23

var

0.23

 penetrate

0.22

 penetr

0.22

 bees

0.21

Activations Density 0.029%

references to cleaning products or their applications

No Comments

No Known Activations