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

 seperate

-0.15

upo

-0.15

antan

-0.15

 frank

-0.14

hle

-0.14

aid

-0.13

enco

-0.13

&eacute

-0.13

 contro

-0.13

æ¼

-0.13

POSITIVE LOGITS

 Hawai

0.17

brig

0.16

åħ

0.15

urations

0.15

.ir

0.14

sip

0.14

gard

0.14

ityEngine

0.14

ä¹ĭ

0.14

tty

0.13

Activations Density 0.000%

No Known Activations

This feature has no known activations.