INDEX

Explanations

mathematical equations and references to calculations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

uro

-0.16

urator

-0.15

tra

-0.15

olle

-0.15

Zak

-0.15

elmet

-0.14

 Cousins

-0.14

íĻ©

-0.14

iben

-0.14

Tel

-0.14

POSITIVE LOGITS

0.15

VOID

0.15

ì¶ľ

0.14

 MetroFramework

0.14

ennial

0.14

 Sass

0.14

reich

0.14

0.13

asion

0.13

aaaaaaaa

0.13

Activations Density 0.059%

mathematical equations and references to calculations

No Comments

No Known Activations