INDEX

Explanations

technical specifications and hardware performance metrics related to computer components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

etri

-0.16

èĥ¶

-0.15

itti

-0.15

agnet

-0.14

wax

-0.13

ÙĨØ©

-0.13

 Pont

-0.13

cov

-0.13

plet

-0.13

Uy

-0.13

POSITIVE LOGITS

OC

0.31

OC

0.29

 overclock

0.24

 stock

0.22

oc

0.22

stock

0.22

 clock

0.22

 bios

0.22

 STOCK

0.22

 clocks

0.22

Activations Density 0.006%

technical specifications and hardware performance metrics related to computer components

No Comments

No Known Activations