INDEX

Explanations

locations and references to 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 @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 Rouge

-0.17

Muk

-0.15

.UnitTesting

-0.15

mour

-0.14

rite

-0.14

ä¸ģ

-0.14

gewater

-0.14

alance

-0.14

trak

-0.14

utenberg

-0.13

POSITIVE LOGITS

Bog

0.34

bog

0.24

Gu

0.22

 ÐĳÐ¾Ð³

0.20

 Vera

0.20

 Guantanamo

0.19

Zac

0.19

 Leon

0.18

 Cart

0.18

 Play

0.17

Activations Density 0.084%

locations and references to specific places

No Comments

No Known Activations