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

antidad

-0.14

 seni

-0.14

 Serif

-0.14

Ä±sÄ±t

-0.14

 Claw

-0.14

 nett

-0.14

$($

-0.13

inois

-0.13

/topics

-0.13

erus

-0.13

POSITIVE LOGITS

ourse

0.15

Ã¼h

0.14

idan

0.14

gba

0.14

XHR

0.14

ecd

0.13

Ø§ÙĨÙĩ

0.13

tons

0.13

aux

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.