INDEX

Explanations

rhetorical questions and expressions of surprise

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

loth

-0.16

lost

-0.14

Hey

-0.14

Yap

-0.14

lak

-0.14

 Heaven

-0.14

ups

-0.13

alling

-0.13

.HTML

-0.13

 Ø§ÙĦØ¨ÙĦ

-0.13

POSITIVE LOGITS

 WRONG

0.33

 wrong

0.32

 Wrong

0.28

Wrong

0.28

 incorrect

0.28

wrong

0.27

 Ð¾ÑĪÐ¸Ð±

0.23

 Incorrect

0.22

 mistaken

0.22

incorrect

0.21

Activations Density 0.101%

rhetorical questions and expressions of surprise

No Comments

No Known Activations