INDEX

Explanations

phrases that involve combining, blending, or intertwining different artistic, scientific, or conceptual elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

adesh

-0.17

à¹Ģà¸īà¸ŀà¸²à¸°

-0.15

à¸ģà¸ķ

-0.15

efon

-0.14

aln

-0.14

oningen

-0.14

à¸Ľà¸£à¸°à¸ģà¸Ńà¸ļ

-0.14

indh

-0.14

ä¼´

-0.13

ked

-0.13

POSITIVE LOGITS

 together

0.36

 worlds

0.33

 disparate

0.32

 elements

0.31

 forces

0.30

 oppos

0.28

 incompatible

0.27

 disciplines

0.27

 dots

0.25

elements

0.24

Activations Density 0.224%

phrases that involve combining, blending, or intertwining different artistic, scientific, or conceptual elements

No Comments

No Known Activations