INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ezier

-0.18

assi

-0.16

erp

-0.13

Ð°ÐºÐ¾Ð²

-0.13

ableViewController

-0.13

ÑĢÐµÐ¶

-0.13

astes

-0.13

.dds

-0.13

Ø¨Ø§Øª

-0.13

akh

-0.13

POSITIVE LOGITS

 also

0.17

ritte

0.15

 Also

0.15

 Ð¿ÑĢÐ¸ÑħÐ¾Ð´

0.14

 ALSO

0.14

ilar

0.14

 scram

0.14

yk

0.14

Also

0.14

oola

0.14

Activations Density 0.045%

No Comments

No Known Activations