INDEX

Explanations

guidance and instructional content related to a product or service

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

isko

-0.15

 Ð¿ÑĢÐ¸

-0.14

 summary

-0.14

ä¼ģ

-0.14

endoza

-0.13

 butterfly

-0.13

etik

-0.13

inst

-0.13

-quote

-0.13

bei

-0.13

POSITIVE LOGITS

 technical

0.17

ÐķÐ¡

0.17

 guides

0.17

 annonces

0.17

æĶ»

0.17

technical

0.15

_TAC

0.15

 Technical

0.14

 Guides

0.14

ħĮ

0.14

Activations Density 0.068%

guidance and instructional content related to a product or service

No Comments

No Known Activations