INDEX

Explanations

quantifiable attributes and specifications of products or devices

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

ding

-0.16

Ã´t

-0.15

leet

-0.14

asal

-0.14

udder

-0.14

utilus

-0.13

_pixels

-0.13

ÑģÑıÑĩ

-0.13

stit

-0.13

apol

-0.13

POSITIVE LOGITS

 identical

0.25

 independent

0.20

 copies

0.19

copies

0.19

 independ

0.18

antan

0.17

 sets

0.17

 separate

0.17

 lanes

0.17

 equally

0.16

Activations Density 0.184%

quantifiable attributes and specifications of products or devices

No Comments

No Known Activations