INDEX

Explanations

information related to geographical locations or specific places

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

 koji

-0.28

 italiano

-0.26

 stesso

-0.25

 electrÃ³nico

-0.24

 completo

-0.22

 himself

-0.20

 ÑıÐºÐ¸Ð¹

-0.19

 franÃ§ais

-0.19

 pÃºblico

-0.19

 ÙĨÙģØ³Ùĩ

-0.18

POSITIVE LOGITS

 herself

0.40

 Î±ÏħÏĦÎ®

0.30

 italiana

0.29

 gratuita

0.27

 pÃºblica

0.27

 ÑģÑĤÐ°Ð»Ð°

0.26

 latina

0.25

 Ð¼Ð¾Ð³Ð»Ð°

0.25

 ÐºÐ¾ÑĤÐ¾ÑĢÐ°Ñı

0.24

 misma

0.24

Activations Density 0.431%

information related to geographical locations or specific places

No Comments

No Known Activations