INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

Ð°ÑĦ

-0.15

æħİ

-0.15

Î¸Î±

-0.14

($.

-0.14

Ø§Ø¯ÙĬ

-0.14

 tasar

-0.14

 Preis

-0.13

 Ð½Ð°ÑĤÑĥ

-0.13

æİª

-0.13

aber

-0.13

POSITIVE LOGITS

cul

0.15

unh

0.14

ar

0.14

 sembl

0.14

arsi

0.14

↵

0.13

ddb

0.13

UCE

0.13

axe

0.13

 tqdm

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.