INDEX

Explanations

geographical locations and addresses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

opro

-0.18

ois

-0.17

 Giles

-0.17

iÅŁ

-0.16

 Microsystems

-0.15

SITE

-0.15

ÑĸÐ¹ÑģÑĮÐºÐ¾ÑĹ

-0.14

 Chow

-0.14

Ãłnh

-0.13

dot

-0.13

POSITIVE LOGITS

Son

0.35

Son

0.32

SON

0.24

son

0.24

 Marin

0.20

 Windsor

0.20

.son

0.20

aiser

0.20

 Sebast

0.19

SON

0.18

Activations Density 0.018%

geographical locations and addresses

No Comments

No Known Activations