INDEX

Explanations

references to programming languages and their features

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

ä¼ı

-0.17

ovu

-0.17

ingles

-0.16

NGX

-0.15

orsi

-0.15

lav

-0.14

rottle

-0.14

 Rever

-0.14

eth

-0.14

 tact

-0.14

POSITIVE LOGITS

 programming

0.25

 Programming

0.24

Programming

0.22

 language

0.22

è¯Ńè¨Ģ

0.21

 languages

0.20

 ÑıÐ·Ñĭ

0.20

 ìĸ¸ìĸ´

0.20

programming

0.19

language

0.19

Activations Density 0.095%

references to programming languages and their features

No Comments

No Known Activations

references to programming languages and their features

No Comments

No Known Activations