INDEX

Explanations

mentions of Korea and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

-0.17

-0.16

ar

-0.16

ern

-0.15

al

-0.15

 Atkins

-0.15

reed

-0.15

-0.14

 Lage

-0.14

 personal

-0.14

POSITIVE LOGITS

agus

0.17

 fisse

0.17

anske

0.16

à¹ĩà¸Ķ

0.15

ÌĤ

0.15

Åº

0.15

.Writer

0.14

adb

0.14

ansson

0.14

shan

0.14

Activations Density 0.014%

mentions of Korea and related terms

No Comments

No Known Activations