INDEX

Explanations

names associated with a specific person or figures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

roe

-0.15

yne

-0.15

ÑĢÐ°ÑĤÐ¸

-0.15

ingroup

-0.15

erdale

-0.15

 å·

-0.14

uxe

-0.14

ÏģÎ¹Ïĥ

-0.14

ISE

-0.14

POSITIVE LOGITS

ãģ£ãģ¨

0.20

 Gian

0.17

bone

0.17

Ã©ra

0.16

agher

0.15

 Amelia

0.15

 componentDid

0.15

thers

0.15

acus

0.15

 Fisher

0.14

Activations Density 0.010%

names associated with a specific person or figures

No Comments

No Known Activations