INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

	↵	↵

-0.19

	↵↵

-0.18

chia

-0.18

eur

-0.17

../../../

-0.17

chai

-0.17

cheng

-0.16

↵

-0.16

zÅĳ

-0.16

Ø¹

-0.16

POSITIVE LOGITS

ÑģÐºÐ»Ð°Ð´

0.23

ehir

0.19

eness

0.19

ndef

0.18

 Ð²Ð¸Ð³Ð»ÑıÐ´Ñĸ

0.18

-thirds

0.17

Ð½ÑĸÐ²ÐµÑĢ

0.16

nd

0.16

dÃ¼r

0.16

inary

0.16

Activations Density 2.119%

No Comments

No Known Activations