INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

gil

-0.20

Ð¾Ð»Ð¾Ð¶

-0.15

Ð°Ð½ÑģÐ¸

-0.15

INGER

-0.15

ave

-0.14

-hop

-0.14

opper

-0.14

inger

-0.14

uil

-0.14

à¥Ģà¤¯

-0.14

POSITIVE LOGITS

urse

0.16

ç¾

0.15

 haft

0.14

 Ansi

0.14

fÃ©

0.14

ectl

0.14

 VERSION

0.14

ÑĤÐ°Ð±

0.14

quota

0.14

zelf

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.