INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

.Automation

-0.16

anko

-0.16

è¥

-0.15

lein

-0.15

QUARE

-0.14

pora

-0.14

å®¾

-0.14

ÙĬÙĥØ§

-0.13

ouis

-0.13

eya

-0.12

POSITIVE LOGITS

 sort

0.27

sort

0.24

ah

0.21

 sorts

0.19

um

0.18

 SORT

0.17

uh

0.17

Sort

0.17

-,

0.17

	sort

0.16

Activations Density 0.000%

No Known Activations

This feature has no known activations.