INDEX

Explanations

terms related to criminal acts or wrongdoing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

aping

-0.17

inkel

-0.16

mie

-0.15

het

-0.15

ilig

-0.15

stral

-0.15

mun

-0.15

åŀ

-0.15

ÎŁÎ

-0.15

eful

-0.15

POSITIVE LOGITS

ution

0.15

elow

0.15

 thoughts

0.15

chin

0.15

card

0.14

incinn

0.14

 regular

0.14

ches

0.13

Ã©es

0.13

Activations Density 0.021%

terms related to criminal acts or wrongdoing

No Comments

No Known Activations