INDEX

Explanations

references to governmental or organizational roles and responsibilities

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

 Orch

-0.14

agh

-0.14

ë©

-0.14

ç¾İ

-0.14

rans

-0.14

yr

-0.13

 Arithmetic

-0.13

embedded

-0.13

reh

-0.13

ook

-0.13

POSITIVE LOGITS

 Ministry

0.54

 ministry

0.49

 ministries

0.38

 Minist

0.31

 minister

0.29

Min

0.29

 Minister

0.28

 ÙĪØ²Ø§Ø±

0.27

 National

0.27

 Cabinet

0.26

Activations Density 0.254%

references to governmental or organizational roles and responsibilities

No Comments

No Known Activations