INDEX

Explanations

instances of specific noteworthy elements or attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 Snyder

-0.14

ensch

-0.13

ctl

-0.13

 status

-0.13

immel

-0.13

hof

-0.13

ules

-0.13

se

-0.13

layui

-0.13

uml

-0.12

POSITIVE LOGITS

 piece

0.31

 molecule

0.28

 item

0.27

piece

0.24

 device

0.22

 organism

0.22

 poem

0.21

 documento

0.21

 masterpiece

0.21

 vessel

0.21

Activations Density 0.076%

instances of specific noteworthy elements or attributes

No Comments

No Known Activations