INDEX

Explanations

references to conspiracy and criminal activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

Gratis

-0.15

Undefined

-0.14

xea

-0.14

Î»Ïī

-0.14

.DOM

-0.14

 olsun

-0.13

reative

-0.13

ennon

-0.13

licer

-0.13

ModelIndex

-0.13

POSITIVE LOGITS

 comp

0.23

 involvement

0.22

 involved

0.20

Ãº

0.19

 conspiracy

0.18

 planning

0.18

 plot

0.18

 coll

0.17

 master

0.17

 Planning

0.17

Activations Density 0.159%

references to conspiracy and criminal activities

No Comments

No Known Activations