INDEX

Explanations

geographical locations and road names

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

uze

-0.17

habi

-0.17

inker

-0.17

ohana

-0.17

AGER

-0.15

/kubernetes

-0.15

uong

-0.14

Tig

-0.14

 HÃ¤

-0.14

-UA

-0.14

POSITIVE LOGITS

logy

0.15

 Ð³ÑĢÐ¸

0.14

bgcolor

0.14

 pend

0.14

 Rodney

0.13

åĳ¢

0.13

Yad

0.13

.ParseException

0.13

 à¤īà¤²

0.13

Activations Density 0.216%

geographical locations and road names

No Comments

No Known Activations