INDEX

Explanations

instances of refusal or rejection in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

ERING

-0.15

omu

-0.14

CHA

-0.14

BOVE

-0.13

auen

-0.13

cha

-0.13

 ZÃ¡p

-0.13

aggable

-0.13

ä¸įè¶³

-0.13

omics

-0.13

POSITIVE LOGITS

 requests

0.31

 invitations

0.30

any

0.30

 pleas

0.27

 offers

0.27

 outright

0.27

 repeated

0.26

requests

0.25

 opportunities

0.24

 suggestions

0.24

Activations Density 0.084%

instances of refusal or rejection in various contexts

No Comments

No Known Activations