INDEX

Explanations

references to authors or individuals that have made contributions or are connected to the content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

lio

-0.17

abar

-0.16

emey

-0.15

 purposes

-0.15

meni

-0.15

bis

-0.14

à¤¿à¤

-0.14

anja

-0.14

 francais

-0.14

POSITIVE LOGITS

 admin

0.26

 Admin

0.23

admin

0.23

_admin

0.21

Admin

0.20

 ADMIN

0.19

Administrator

0.18

 Unknown

0.17

 Administrator

0.17

.admin

0.17

Activations Density 0.026%

references to authors or individuals that have made contributions or are connected to the content

No Comments

No Known Activations