INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

mage

-0.15

theon

-0.14

rib

-0.14

bere

-0.14

 Arch

-0.13

veau

-0.13

ÐµÐ½Ð´

-0.13

è£ı

-0.13

à¸£à¸ĵ

-0.13

ÑĢÐ°Ð³

-0.13

POSITIVE LOGITS

Äįe

0.16

uckles

0.15

veh

0.14

olor

0.14

)NULL

0.14

.LENGTH

0.14

FFFFFFFF

0.13

ãģĹãģ¦ãĤĤ

0.13

æľ¬å½ĵ

0.13

dip

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.