INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Ð¾Ð¶Ð´ÐµÐ½Ð¸Ñı

-0.15

eph

-0.15

è¼ª

-0.14

ãĥ³ãĤ°

-0.13

esto

-0.13

 ìĿĳ

-0.13

cole

-0.13

Ep

-0.13

resher

-0.13

ro

-0.13

POSITIVE LOGITS

 Saud

0.15

otte

0.15

mor

0.14

lb

0.14

RATE

0.14

@$_

0.14

cesso

0.14

ural

0.14

ansson

0.14

 policy

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.