INDEX

Explanations

references to prominent events in various industries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

Î»Î®

-0.15

-0.14

Kar

-0.14

ued

-0.14

kar

-0.14

 Stall

-0.14

 Cable

-0.14

ensen

-0.14

Cum

-0.14

oley

-0.14

POSITIVE LOGITS

 events

0.32

events

0.30

event

0.28

 Events

0.27

_events

0.26

Events

0.26

 EVENTS

0.26

 eventos

0.26

 event

0.26

 festivals

0.25

Activations Density 0.182%

references to prominent events in various industries

No Comments

No Known Activations