INDEX

Explanations

references to compliance and legal obligations

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

ubb

-0.18

ëĬ¥

-0.16

URT

-0.15

è½®

-0.14

zel

-0.14

rick

-0.13

rian

-0.13

à¸±à¸¨

-0.13

 unbiased

-0.13

shift

-0.13

POSITIVE LOGITS

 compliance

0.46

 violation

0.43

 violations

0.42

 Compliance

0.42

 viol

0.40

 Viol

0.39

 comply

0.35

 compliant

0.35

 violate

0.34

 violating

0.34

Activations Density 0.198%

references to compliance and legal obligations

No Comments

No Known Activations