INDEX

Explanations

references to groups or individuals sharing similar traits or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

phere

-0.20

elsing

-0.17

thane

-0.16

urge

-0.16

xon

-0.15

eu

-0.14

ç¯Ģ

-0.14

deps

-0.13

tram

-0.13

kara

-0.13

POSITIVE LOGITS

 alike

0.15

Wed

0.14

wed

0.13

 Millet

0.13

RefreshLayout

0.13

Uph

0.13

kowski

0.13

tal

0.13

 tren

0.13

Bracket

0.13

Activations Density 0.003%

references to groups or individuals sharing similar traits or experiences

No Comments

No Known Activations