INDEX

Explanations

references to illegal activities and violations

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

utral

-0.16

.ns

-0.15

à¤¨à¤²

-0.15

lemetry

-0.14

ç©į

-0.14

ãģĨãģ¡

-0.14

Ã¥

-0.14

 kÃ¥

-0.14

aÄį

-0.13

getAs

-0.13

POSITIVE LOGITS

/il

0.19

ely

0.16

zza

0.15

ude

0.15

woke

0.15

amate

0.15

ities

0.14

usty

0.14

/un

0.14

enter

0.14

Activations Density 0.017%

references to illegal activities and violations

No Comments

No Known Activations