INDEX

Explanations

terms related to rendering processes in programming or graphics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ty

-0.16

zech

-0.15

ulla

-0.15

ustin

-0.15

udge

-0.15

yl

-0.15

ades

-0.15

pt

-0.15

eck

-0.14

POSITIVE LOGITS

ings

0.27

ers

0.24

.Render

0.21

izador

0.20

INGS

0.20

edImage

0.20

izar

0.20

issance

0.19

izado

0.19

ëŁ¬

0.19

Activations Density 0.021%

terms related to rendering processes in programming or graphics

No Comments

No Known Activations