INDEX

Explanations

references to future content or related information that will be elaborated on later

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

IELD

-0.15

å½ĵ

-0.15

opak

-0.15

ãĥ³ãĥĸ

-0.14

ÄŁinden

-0.14

regor

-0.14

ined

-0.14

enville

-0.14

opez

-0.14

áº¿

-0.14

POSITIVE LOGITS

ÙĪÙĬÙĥ

0.15

itzer

0.15

ãģ£ãģ¡

0.15

zych

0.15

ìĬ¤ì½Ķ

0.15

calar

0.14

mainwindow

0.14

adding

0.14

artner

0.14

urre

0.13

Activations Density 0.062%

references to future content or related information that will be elaborated on later

No Comments

No Known Activations