INDEX

Explanations

references to the United Nations and its activities

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

 Cant

-0.15

 Mund

-0.14

ç³»

-0.14

coat

-0.14

 Moody

-0.14

↵

-0.14

 convention

-0.14

-io

-0.14

å·¥

-0.14

 Congress

-0.14

POSITIVE LOGITS

 Security

0.36

UNS

0.34

Security

0.31

 council

0.27

 SECURITY

0.24

ouncil

0.23

 Council

0.23

Council

0.23

ecurity

0.23

security

0.22

Activations Density 0.029%

references to the United Nations and its activities

No Comments

No Known Activations