INDEX

Explanations

mentions of favorite books, movies, and personal achievements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

uluk

-0.19

)row

-0.17

cce

-0.16

oling

-0.16

ãģĵãĤĵãģ«ãģ¡ãģ¯

-0.15

/mainwindow

-0.14

ippi

-0.14

alyzed

-0.14

uitka

-0.14

 VerfÃ¼gung

-0.14

POSITIVE LOGITS

 moments

0.18

0.14

 traits

0.14

 Burgess

0.14

 characteristics

0.14

_TRA

0.14

 functional

0.14

IE

0.13

 mental

0.13

Activations Density 0.351%

mentions of favorite books, movies, and personal achievements

No Comments

No Known Activations