INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ixel

-0.14

rire

-0.14

que

-0.14

ViewChild

-0.14

EC

-0.14

ec

-0.14

Ø§Ø¨ÙĦ

-0.13

aat

-0.13

ghi

-0.13

yny

-0.13

POSITIVE LOGITS

æ´¾

0.14

Ø¹ÙĬØ©

0.13

 amet

0.13

 tato

0.13

aget

0.13

iaux

0.13

Ã¶rÃ¼

0.13

avit

0.12

erea

0.12

å¯Ħ

0.12

Activations Density 0.000%

No Known Activations

This feature has no known activations.