INDEX

Explanations

references to warfare and military experiences

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

Not in Any Lists

No Comments

Negative Logits

ammad

-0.16

adle

-0.15

ç¿¼

-0.15

 Bowman

-0.14

 retro

-0.14

 State

-0.14

ĳľ

-0.14

å¥´

-0.14

 seal

-0.14

POSITIVE LOGITS

 trenches

0.26

0.25

 trench

0.24

Vim

0.20

 poil

0.18

shell

0.18

WW

0.17

 sector

0.17

 Belgium

0.17

 mort

0.16

Activations Density 0.133%

references to warfare and military experiences

No Comments

No Known Activations