INDEX

Explanations

phrases related to notable achievements or attributes of individuals and companies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

.EventQueue

-0.14

ìĤ¬ë¬´

-0.13

 Americas

-0.13

 newInstance

-0.13

 Rencontres

-0.13

segue

-0.12

/MPL

-0.12

alarÄ±

-0.12

andum

-0.12

angkan

-0.12

POSITIVE LOGITS

uchar

0.15

ients

0.15

hed

0.15

oret

0.13

emic

0.13

udos

0.13

edl

0.13

ysa

0.13

apos

0.13

idel

0.13

Activations Density 0.801%

phrases related to notable achievements or attributes of individuals and companies

No Comments

No Known Activations