INDEX

Explanations

references to events, opportunities, and calls for donations or applications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

anou

-0.16

ingo

-0.16

Bid

-0.15

 Immediate

-0.14

itative

-0.14

bid

-0.14

mill

-0.14

ulti

-0.14

antium

-0.14

.viewDidLoad

-0.13

POSITIVE LOGITS

©

0.15

SF

0.15

eres

0.15

æīķ

0.15

ãĥ¼ãĥŀ

0.15

aar

0.14

 Team

0.14

ļ

0.14

,callback

0.14

lah

0.14

Activations Density 0.230%

references to events, opportunities, and calls for donations or applications

No Comments

No Known Activations