INDEX

Explanations

terms related to geographic and cultural identity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

 presente

-0.17

 ÐºÐ¾ÑĤÐ¾ÑĢÐ°Ñı

-0.17

 itself

-0.16

 ÐºÐ¾ÑĤÐ¾ÑĢÑĭÐ¹

-0.16

 ÑıÐºÐ¸Ð¹

-0.15

 Î±ÏħÏĦÎ®

-0.15

 ÐºÐ¾ÑĤÐ¾ÑĢÑĥÑİ

-0.15

 Bever

-0.15

 Chips

-0.14

POSITIVE LOGITS

 themselves

0.28

 ones

0.24

ones

0.20

 Ones

0.19

 denen

0.18

 koje

0.18

maal

0.18

 ÐºÐ¾ÑĤÐ¾ÑĢÑĭÐµ

0.18

ÃŃveis

0.18

 gratuits

0.17

Activations Density 0.160%

terms related to geographic and cultural identity

No Comments

No Known Activations