INDEX

Explanations

the presence of author attribution in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

kinson

-0.15

Uns

-0.14

ÃŃm

-0.14

rote

-0.14

-0.13

odd

-0.13

iously

-0.13

ture

-0.13

POSITIVE LOGITS

 admin

0.40

 Admin

0.34

Admin

0.33

admin

0.32

_admin

0.30

 Administrator

0.30

Administrator

0.28

 administrator

0.28

_ADMIN

0.26

-admin

0.26

Activations Density 0.032%

the presence of author attribution in the text

No Comments

No Known Activations