INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

oner

-0.17

irie

-0.16

eter

-0.15

zk

-0.15

ereotype

-0.14

Ø®Ø§ÙĨÙĩ

-0.14

spir

-0.14

 cÃ²n

-0.14

quet

-0.14

 Ø¨Ø§Ø¹

-0.14

POSITIVE LOGITS

ances

0.26

antly

0.23

/dis

0.22

ance

0.18

adox

0.17

ANCES

0.17

ìĥĪ

0.17

åĭ¢

0.16

nces

0.16

alker

0.16

Activations Density 0.034%

No Comments

No Known Activations