INDEX

Explanations

references to advisory bodies and committees involved in governance or oversight

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

 chÃ¢n

-0.17

 queryInterface

-0.16

esine

-0.15

æ¾

-0.15

 Innoc

-0.15

CriticalSection

-0.15

vero

-0.15

éĺħè¯»æ¬¡æķ°

-0.15

 rall

-0.15

reon

-0.15

POSITIVE LOGITS

 members

0.20

imon

0.16

 member

0.16

 conc

0.15

 torture

0.15

ears

0.15

 abuse

0.14

 misuse

0.14

uth

0.14

 panel

0.14

Activations Density 0.250%

references to advisory bodies and committees involved in governance or oversight

No Comments

No Known Activations