INDEX

Explanations

terms related to legal consequences and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

intr

-0.16

 siege

-0.15

olit

-0.14

 Siege

-0.14

ahlen

-0.14

QN

-0.14

 assail

-0.14

 Vulner

-0.14

 Intr

-0.13

POSITIVE LOGITS

vero

0.16

reserved

0.16

zÃ¡

0.15

éĻ

0.15

èº

0.15

 RESERVED

0.15

 reserved

0.15

 ÙģÙĩØ±Ø³Øª

0.15

/*****************************************************************************↵

0.15

iline

0.14

Activations Density 0.120%

terms related to legal consequences and regulations

No Comments

No Known Activations