INDEX

Explanations

concepts related to comparison and relationships between different entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

âķĹ

-0.16

á»ĳt

-0.15

ante

-0.14

 ABOVE

-0.14

zos

-0.14

omu

-0.14

Ø¨Ø§ÙĦ

-0.14

bei

-0.13

ÑĢÐ¾Ñģ

-0.13

ares

-0.13

POSITIVE LOGITS

 another

0.41

 others

0.35

another

0.33

 Another

0.29

åı¦ä¸Ģ

0.28

Another

0.28

others

0.27

åı¦

0.27

 otro

0.26

 ones

0.25

Activations Density 0.071%

concepts related to comparison and relationships between different entities

No Comments

No Known Activations