INDEX

Explanations

keywords related to scientific institutions and research entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

stav

-0.15

\OptionsResolver

-0.15

adera

-0.15

.epam

-0.15

ÐµÐºÑĤÑĥ

-0.14

iesz

-0.14

vaz

-0.14

 ÙĨØ¹

-0.14

 Intellectual

-0.14

ãģĦãĤĦ

-0.14

POSITIVE LOGITS

 Italian

0.23

 Polo

0.22

Italian

0.21

(It

0.20

 Italy

0.20

 Fond

0.20

 italian

0.20

Italy

0.19

Tus

0.19

 Luigi

0.19

Activations Density 0.066%

keywords related to scientific institutions and research entities

No Comments

No Known Activations