INDEX

Explanations

phrases that indicate potential actions and collaborations

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

ament

-0.17

inqu

-0.16

gado

-0.16

ehler

-0.16

ãĥ¼ãĥĵ

-0.14

aza

-0.14

 fron

-0.14

inkle

-0.14

 Editor

-0.13

nÃŃ

-0.13

POSITIVE LOGITS

tero

0.15

 Jaune

0.15

Jar

0.14

yaw

0.14

ellig

0.14

jure

0.14

 Mund

0.14

İ·

0.14

HandlerContext

0.13

adlo

0.13

Activations Density 0.068%

phrases that indicate potential actions and collaborations

No Comments

No Known Activations