INDEX

Explanations

comparative phrases that express degrees of similarity or quality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

acin

-0.17

CREMENT

-0.15

ieten

-0.15

asted

-0.15

msp

-0.14

MBER

-0.14

ì£¼ìĿĺ

-0.14

Ã©li

-0.14

">ÃĹ</

-0.14

erate

-0.14

POSITIVE LOGITS

 possible

0.31

 Possible

0.25

 ever

0.25

 possÃŃvel

0.24

 posible

0.23

possible

0.23

Possible

0.22

 possibile

0.21

can

0.20

 Ð¼Ð¾Ð¶Ð½Ð¾

0.20

Activations Density 0.047%

comparative phrases that express degrees of similarity or quality

No Comments

No Known Activations