INDEX

Explanations

technical terms related to computer graphics and particle systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ime

-0.15

tere

-0.14

inel

-0.14

osy

-0.14

åį·

-0.14

 session

-0.14

FindObject

-0.14

Geh

-0.13

acher

-0.13

 convo

-0.13

POSITIVE LOGITS

 normals

0.24

 vertices

0.21

 glVertex

0.20

 indices

0.20

 vertex

0.20

AttribPointer

0.20

 Norm

0.19

 triangles

0.19

Indices

0.18

.vertex

0.18

Activations Density 0.017%

technical terms related to computer graphics and particle systems

No Comments

No Known Activations