INDEX

Explanations

references to specific locations or geographical identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

land

-0.14

eros

-0.14

ouser

-0.14

Å¥

-0.13

ä¹ĭä¸Ģ

-0.13

 elÃ©

-0.13

Bal

-0.13

 Drag

-0.13

resher

-0.13

ysa

-0.13

POSITIVE LOGITS

ogne

0.18

shint

0.17

łí

0.17

 Ä°li

0.14

Ð°ÑĢÑĩ

0.14

entine

0.14

WithOptions

0.14

ajan

0.14

Frameworks

0.14

eyim

0.14

Activations Density 0.087%

references to specific locations or geographical identifiers

No Comments

No Known Activations