INDEX

Explanations

references to software versions and assembly information

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

à¸¥à¸°

-0.16

olet

-0.15

HQ

-0.15

ilot

-0.15

.getvalue

-0.15

EGA

-0.14

izon

-0.14

andid

-0.14

uky

-0.14

ÑĸÐ·

-0.14

POSITIVE LOGITS

 project

0.29

 Project

0.24

project

0.23

 projektu

0.22

proj

0.21

Project

0.21

-project

0.21

 projekt

0.20

 projectName

0.20

_project

0.20

Activations Density 0.043%

references to software versions and assembly information

No Comments

No Known Activations