INDEX

Explanations

references to the brand "Vevo."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

aid

-0.16

rim

-0.16

 ÑĥÑģ

-0.16

cott

-0.15

 Ð¿Ð¾Ñģ

-0.15

fon

-0.15

ieee

-0.14

aro

-0.14

xm

-0.14

mun

-0.14

POSITIVE LOGITS

iled

0.22

LOCITY

0.21

iculos

0.20

illard

0.19

olia

0.19

leigh

0.18

icles

0.17

illance

0.17

ILED

0.17

ITCH

0.17

Activations Density 0.022%

references to the brand "Vevo."

No Comments

No Known Activations