INDEX

Explanations

metrics and measurements related to workout performance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

Mapped

-0.15

UnderTest

-0.15

orex

-0.14

tsky

-0.14

/pre

-0.14

ors

-0.14

orsch

-0.14

 whose

-0.14

tered

-0.14

adm

-0.13

POSITIVE LOGITS

-count

0.23

count

0.23

 count

0.21

æķ°

0.21

/frame

0.17

PerPixel

0.17

 Count

0.17

Count

0.17

 Redistributions

0.17

-per

0.17

Activations Density 0.121%

metrics and measurements related to workout performance

No Comments

No Known Activations