INDEX

Explanations

information about organizational structure and membership details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

mani

-0.16

zie

-0.16

.ObjectModel

-0.15

æĭħå½ĵ

-0.15

dyn

-0.14

insk

-0.14

ahas

-0.14

 surv

-0.14

onas

-0.14

 ÐĿÐ°ÑĤ

-0.14

POSITIVE LOGITS

 membership

0.63

 Membership

0.57

membership

0.55

Membership

0.50

 memberships

0.49

 member

0.48

-members

0.46

 members

0.43

 Member

0.41

 Mitgli

0.41

Activations Density 0.195%

information about organizational structure and membership details

No Comments

No Known Activations