INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ODEV

-0.15

ecko

-0.15

Advertisements

-0.14

"Yeah

-0.14

argin

-0.14

 anybody

-0.14

Ø§Ø¨ÙĬ

-0.13

inalg

-0.13

 EITHER

-0.13

_$

-0.13

POSITIVE LOGITS

 ourselves

0.14

 remix

0.13

 reuse

0.13

 dear

0.13

å¦ĤæŃ¤

0.13

 GÃ¤

0.13

Our

0.13

Ã¨les

0.13

 ìĿ´ëĬĶ

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.