INDEX

Explanations

titles and references related to films and movies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

Ð»Ð¾Ð¼

-0.16

aea

-0.15

hek

-0.14

ãĤĩãģĨ

-0.14

SEQUENTIAL

-0.14

usher

-0.14

anzeigen

-0.14

rish

-0.13

bis

-0.13

POSITIVE LOGITS

 follows

0.37

 centers

0.35

 stars

0.32

 follow

0.31

 centres

0.30

 about

0.28

centers

0.28

 center

0.28

 centered

0.27

follow

0.26

Activations Density 0.223%

titles and references related to films and movies

No Comments

No Known Activations