INDEX

Explanations

references to individuals and their professional expertise or background

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

 vulner

-0.15

utta

-0.15

 dziewcz

-0.15

.setResult

-0.14

rist

-0.14

olg

-0.14

ambi

-0.14

oro

-0.13

loat

-0.13

ÑıÑĩ

-0.13

POSITIVE LOGITS

 former

0.40

 background

0.37

 backgrounds

0.35

former

0.35

 prior

0.33

 Former

0.33

 previous

0.31

 Background

0.31

background

0.29

Former

0.28

Activations Density 0.241%

references to individuals and their professional expertise or background

No Comments

No Known Activations