INDEX

Explanations

references to historical figures and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

iland

-0.15

á»ģn

-0.15

abyrin

-0.15

IFn

-0.14

mbH

-0.14

raphics

-0.14

 åľ

-0.14

 ÑģÐºÐ°Ð·

-0.13

locks

-0.13

Orth

-0.13

POSITIVE LOGITS

 Roman

0.40

Roman

0.35

 Rome

0.35

 Romans

0.31

 senator

0.30

 Pompe

0.30

 roman

0.29

 Caesar

0.28

 Roma

0.28

 Senator

0.27

Activations Density 0.113%

references to historical figures and events

No Comments

No Known Activations