INDEX

Explanations

numerical data or statistics related to groups and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

par

-0.18

ito

-0.17

 minded

-0.16

awe

-0.16

hc

-0.15

è¡Ľ

-0.15

ott

-0.15

ney

-0.15

-0.14

opia

-0.14

POSITIVE LOGITS

VRT

0.17

isha

0.16

æĹ¢

0.15

iversite

0.15

 pornos

0.15

strup

0.14

abox

0.14

erli

0.14

LOUR

0.14

_invoke

0.14

Activations Density 0.022%

numerical data or statistics related to groups and events

No Comments

No Known Activations