INDEX

Explanations

phrases and terms related to performance, effectiveness, and efficiency in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

UGE

-0.15

 Riot

-0.15

ilty

-0.15

 Mojo

-0.14

riÃ¨re

-0.13

-roll

-0.13

 Pathfinder

-0.13

illo

-0.13

 Beck

-0.13

 Army

-0.13

POSITIVE LOGITS

 cost

0.28

 effective

0.27

 user

0.26

effective

0.25

cost

0.24

 efect

0.24

 EFFECT

0.23

Effective

0.23

_effect

0.23

user

0.22

Activations Density 0.155%

phrases and terms related to performance, effectiveness, and efficiency in various contexts

No Comments

No Known Activations