INDEX

Explanations

phrases indicating the presence or inclusion of specific items or features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Ð¶Ðµ

-0.18

ieres

-0.15

 pÅĻÃŃpadnÄĽ

-0.14

arlo

-0.14

ï½¥

-0.13

andr

-0.13

acos

-0.13

Ø¹

-0.13

 Others

-0.12

oris

-0.12

POSITIVE LOGITS

 both

0.28

 neither

0.24

 mostly

0.23

 ÑģÐ¾Ð±Ð¾Ð¹

0.23

 mainly

0.23

 nothing

0.23

 elements

0.22

 only

0.22

 everything

0.22

 plenty

0.21

Activations Density 0.291%

phrases indicating the presence or inclusion of specific items or features

No Comments

No Known Activations