INDEX

Explanations

terms related to flow dynamics and wave behavior

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

Æ°Æ¡ng

-0.16

 wheel

-0.14

ìĭ¸

-0.14

Geh

-0.14

 rates

-0.14

Assignable

-0.14

.null

-0.13

iew

-0.13

 Cycling

-0.13

uhn

-0.13

POSITIVE LOGITS

 solitary

0.25

 DISP

0.23

 disp

0.23

 dispersion

0.21

 Disp

0.20

disp

0.20

 Benjamin

0.19

sho

0.19

cn

0.19

Disp

0.18

Activations Density 0.078%

terms related to flow dynamics and wave behavior

No Comments

No Known Activations