INDEX

Explanations

key examples and significant cases within various contexts and discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 chá»©

-0.16

zh

-0.14

 ranging

-0.14

zcze

-0.14

 Exists

-0.13

Iso

-0.13

ISO

-0.13

origin

-0.13

 zwar

-0.12

 principalmente

-0.12

POSITIVE LOGITS

is

0.32

çļĦæĺ¯

0.29

å°±æĺ¯

0.27

 include

0.24

was

0.23

 adalah

0.22

ãģ®ãģ¯

0.21

 Ø¹Ø¨Ø§Ø±Øª

0.20

 happens

0.19

 involves

0.19

Activations Density 0.222%

key examples and significant cases within various contexts and discussions

No Comments

No Known Activations