INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

yssey

-0.16

odiac

-0.15

chet

-0.15

urga

-0.14

/loose

-0.13

-INF

-0.13

ucid

-0.13

 voluntarily

-0.13

Ð¾Ð±Ñĭ

-0.13

ayers

-0.13

POSITIVE LOGITS

rupa

0.16

à¹Ģà¸ªà¸Ļ

0.15

ROP

0.15

holm

0.15

leigh

0.14

obel

0.14

achts

0.14

lain

0.14

unh

0.14

 Commissioner

0.14

Activations Density 0.000%

No Known Activations

This feature has no known activations.