INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

onen

-0.18

Kov

-0.16

icmp

-0.15

gency

-0.15

hausen

-0.14

ulen

-0.14

inear

-0.14

iá»ģm

-0.14

 Becker

-0.13

Periph

-0.13

POSITIVE LOGITS

acos

0.16

 Shel

0.15

 bÃ¬nh

0.14

tems

0.14

Ru

0.14

zdy

0.13

 getStatus

0.13

 Ø¯ÙĪØ¨

0.13

ERSHEY

0.13

 McLaren

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.