INDEX

Explanations

specific formatting or encoding issues within text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ihan

-0.17

 Dane

-0.15

zyst

-0.14

.scalablytyped

-0.14

filme

-0.14

Rom

-0.13

CMS

-0.13

arranty

-0.13

lood

-0.13

abbit

-0.13

POSITIVE LOGITS

 apex

0.26

 region

0.25

 Region

0.24

 Apex

0.24

 regional

0.22

 REGION

0.22

 Regional

0.22

 Regions

0.21

APE

0.21

 Page

0.21

Activations Density 0.007%

specific formatting or encoding issues within text

No Comments

No Known Activations