INDEX

Explanations

references to hacking activities and hackers

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

 kiá»ĩn

-0.15

ebi

-0.15

ccione

-0.15

ales

-0.14

rowse

-0.14

 hawk

-0.14

sian

-0.14

engeance

-0.13

Ð»Ð¸ÑĨ

-0.13

oodoo

-0.13

POSITIVE LOGITS

uffman

0.15

ibur

0.15

intosh

0.15

ICI

0.14

zw

0.14

NTN

0.14

ANCELED

0.14

libft

0.13

jax

0.13

ceph

0.13

Activations Density 0.021%

references to hacking activities and hackers

No Comments

No Known Activations