INDEX

Explanations

references to job interviews

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ovit

-0.17

erland

-0.15

obo

-0.15

readcr

-0.15

ilded

-0.15

 Gott

-0.14

lund

-0.14

omik

-0.14

 Barnett

-0.13

 lÆ°á»£ng

-0.13

POSITIVE LOGITS

ees

0.19

doch

0.16

à¸¡à¸²à¸ģà¸¡à¸²à¸¢

0.15

ined

0.14

ÐµÐ½Ñģ

0.14

.WinForms

0.14

getSingleton

0.14

á»ĳt

0.14

ee

0.14

Activations Density 0.013%

references to job interviews

No Comments

No Known Activations