INDEX

Explanations

references to packing and organization of items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Package

-0.23

_package

-0.21

 Package

-0.20

 Packages

-0.19

Packet

-0.19

 package

-0.18

 packaged

-0.18

-packages

-0.18

 packages

-0.18

Packages

-0.18

POSITIVE LOGITS

aged

0.36

aging

0.34

AGING

0.27

agers

0.26

è£

0.25

ager

0.24

rat

0.23

 deal

0.23

AGED

0.23

 lunches

0.22

Activations Density 0.046%

references to packing and organization of items

No Comments

No Known Activations