INDEX

Explanations

corporate and regulatory information related to media and organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 problem

-0.23

 Problem

-0.19

problem

-0.18

Problem

-0.17

 problema

-0.17

 proble

-0.17

och

-0.16

 objection

-0.15

eil

-0.15

ë¬¸ìłľ

-0.15

POSITIVE LOGITS

 registered

0.24

 registration

0.24

registered

0.22

 Registered

0.22

 Registration

0.22

çĻ»éĮ²

0.21

 REGISTER

0.20

 unregister

0.20

æ³¨åĨĮ

0.20

.Register

0.20

Activations Density 0.084%

corporate and regulatory information related to media and organizations

No Comments

No Known Activations