INDEX

Explanations

references to diplomatic talks involving North and South Korea

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ÑıÐ·

-0.16

 GENERIC

-0.15

Î³Î¬

-0.15

å¤ķ

-0.14

 Sabb

-0.14

ÑıÑĤ

-0.14

cznie

-0.14

adu

-0.14

ithe

-0.13

POSITIVE LOGITS

 Korean

0.43

 Pyongyang

0.41

 Korea

0.40

Kim

0.37

 Koreans

0.36

 North

0.36

 Seoul

0.35

DPR

0.35

Kim

0.31

North

0.30

Activations Density 0.038%

references to diplomatic talks involving North and South Korea

No Comments

No Known Activations