INDEX

Explanations

mathematical notations and concepts related to geometry and coordinates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ostel

-0.17

-bordered

-0.16

 Orientation

-0.16

.Rectangle

-0.15

 undermin

-0.15

Ø¶Ùħ

-0.15

ç¸

-0.14

orra

-0.14

à¸Īà¸³

-0.14

pty

-0.14

POSITIVE LOGITS

 points

0.41

 point

0.38

 Points

0.37

-points

0.33

 Point

0.33

points

0.32

Points

0.30

-point

0.30

 ÑĤÐ¾ÑĩÐºÐ¸

0.29

_points

0.28

Activations Density 0.172%

mathematical notations and concepts related to geometry and coordinates

No Comments

No Known Activations