INDEX

Explanations

references to regulatory compliance and enforcement actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

æ»ħ

-0.16

atron

-0.15

borg

-0.15

_dropout

-0.14

getBlock

-0.14

/ws

-0.13

exter

-0.13

zero

-0.13

tember

-0.13

áº£m

-0.13

POSITIVE LOGITS

 viol

0.71

 violation

0.68

 Viol

0.66

 violations

0.63

 violating

0.62

 violate

0.61

 violated

0.58

-viol

0.57

viol

0.56

 violates

0.55

Activations Density 0.594%

references to regulatory compliance and enforcement actions

No Comments

No Known Activations