INDEX

Explanations

terms related to asynchronous and synchronous processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ters

-0.17

adiator

-0.16

ÐľÐŀ

-0.16

-unstyled

-0.15

ty

-0.15

late

-0.14

 latter

-0.14

ughter

-0.14

ties

-0.14

tf

-0.14

POSITIVE LOGITS

ron

0.49

rh

0.39

RON

0.30

ronic

0.28

rone

0.28

ÑĢÐ¾Ð½

0.24

0.23

rons

0.23

rowave

0.21

rou

0.20

Activations Density 0.018%

terms related to asynchronous and synchronous processes

No Comments

No Known Activations