INDEX

Explanations

references to third-party entities or individuals

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

ulu

-0.17

iegel

-0.15

ulk

-0.15

ovit

-0.14

czy

-0.14

à¹Īà¸Ńà¸Ļ

-0.14

blems

-0.14

rypton

-0.14

Outlet

-0.14

pery

-0.14

POSITIVE LOGITS

 third

0.34

 Third

0.32

Third

0.30

third

0.29

-third

0.28

 THIRD

0.28

 ç¬¬ä¸ī

0.27

-party

0.27

ç¬¬ä¸ī

0.26

_third

0.24

Activations Density 0.009%

references to third-party entities or individuals

No Comments

No Known Activations