INDEX

Explanations

references to notable individuals and their achievements

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

onia

-0.17

onus

-0.16

atak

-0.16

urus

-0.15

æĹ

-0.15

hong

-0.15

'gc

-0.15

.mix

-0.14

afi

-0.14

airo

-0.14

POSITIVE LOGITS

 remembered

0.24

 most

0.23

 known

0.21

 famous

0.21

 bekannt

0.20

 famously

0.20

 familiar

0.20

 popular

0.19

Known

0.19

 Known

0.19

Activations Density 0.075%

references to notable individuals and their achievements

No Known Activations