INDEX

Explanations

content related to product specifications, reviews, and guarantees

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

ude

-0.15

vic

-0.14

Ã«

-0.14

ĶĦ

-0.14

atos

-0.13

olt

-0.13

[__

-0.13

æľ

-0.13

atta

-0.13

POSITIVE LOGITS

Ð»Ð¸ÐºÐ°

0.15

lland

0.15

nier

0.14

Ð»Ð¸ÑĪÐºÐ¾Ð¼

0.14

 Burl

0.14

uti

0.14

egov

0.14

 TÃłi

0.14

 RESERVED

0.13

 Ø§ÙĦØ¬Ùħ

0.13

Activations Density 0.185%

content related to product specifications, reviews, and guarantees

No Comments

No Known Activations