INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ungan

-0.15

ãĤ

-0.14

 ÙĩÙħÚĨÙĨÛĮÙĨ

-0.14

-0.13

igor

-0.13

ollo

-0.13

Ø³Ø§Ø²ÛĮ

-0.13

.gnu

-0.13

ÅĤem

-0.13

marshall

-0.13

POSITIVE LOGITS

 tvar

0.16

 soph

0.16

 Spell

0.15

alue

0.15

 Fancy

0.15

uards

0.14

ozem

0.14

inalg

0.14

gard

0.14

 Morg

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.