INDEX

Explanations

elements related to legal and political terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ÑĸÐ¹ÑģÑĮÐºÐ¾ÑĹ

-0.31

 della

-0.26

dei

-0.21

 delle

-0.20

enskÃ©

-0.18

 ÑĤÐ°ÐºÐ¾Ð¹

-0.18

rovÃ©

-0.17

 ÑįÑĤÐ¾Ð¹

-0.17

 ÑģÐ°Ð¼Ð¾Ð¹

-0.17

tej

-0.17

POSITIVE LOGITS

nego

0.29

zego

0.28

owego

0.26

ÐºÐ¾Ð³Ð¾

0.26

kiego

0.25

Ð¾Ð³Ð¾

0.25

iego

0.25

Ð°Ð½Ð¾Ð³Ð¾

0.24

ÐµÐ½Ð¾Ð³Ð¾

0.24

ÑĩÐµÑģÐºÐ¾Ð³Ð¾

0.23

Activations Density 0.030%

elements related to legal and political terms

No Comments

No Known Activations