INDEX

Explanations

comparative phrases that assess superiority or inferiority

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

 Prev

-0.15

iden

-0.15

ker

-0.15

æ··åĲĪ

-0.14

_PICTURE

-0.14

 Rubio

-0.14

illus

-0.14

urga

-0.14

stagram

-0.14

ä¸įäºĨ

-0.14

POSITIVE LOGITS

 original

0.22

 originals

0.20

original

0.19

 direct

0.19

ORIGINAL

0.18

åİŁå§ĭ

0.18

direct

0.18

 Ð¾ÑĢÐ¸Ð³

0.17

çĽ´æİ¥

0.17

straight

0.17

Activations Density 0.005%

comparative phrases that assess superiority or inferiority

No Comments

No Known Activations