INDEX

Explanations

references to Japan and Japanese culture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

amos

-0.16

ahu

-0.16

apore

-0.15

/latest

-0.14

 Observatory

-0.14

BITS

-0.14

vic

-0.14

jay

-0.14

incare

-0.14

 labore

-0.14

POSITIVE LOGITS

 æĹ¥æľ¬

0.18

esel

0.18

ãĢģæĹ¥æľ¬

0.18

 sushi

0.17

kami

0.17

apon

0.16

 japanese

0.16

 ÚĺØ§Ù¾

0.16

 Japon

0.16

nier

0.16

Activations Density 0.109%

references to Japan and Japanese culture

No Comments

No Known Activations