INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

-0.14

ãĥ©ãĤ¤ãĥ³

-0.14

 fore

-0.14

Î¸Ïħ

-0.14

hoa

-0.14

cop

-0.14

ãĥ¼ãĤ¿

-0.14

ubl

-0.13

hle

-0.13

ouver

-0.13

POSITIVE LOGITS

ÙĨØ´

0.15

 Institution

0.14

ãĥ¯ãĤ¤ãĥĪ

0.14

appa

0.14

0.13

Cam

0.13

zw

0.13

isto

0.13

ss

0.13

vt

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.