INDEX

Explanations

references to geographical regions, particularly South and North America

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

eba

-0.17

orda

-0.17

arde

-0.15

itere

-0.15

ursors

-0.15

stal

-0.15

Ãºt

-0.15

cip

-0.14

alous

-0.14

¨ìĸ´

-0.14

POSITIVE LOGITS

yp

0.14

ãĥĥãĥĦ

0.14

 rose

0.14

ser

0.13

 ambient

0.13

 dissoci

0.13

Ser

0.13

 facts

0.13

Activations Density 0.045%

references to geographical regions, particularly South and North America

No Comments

No Known Activations