INDEX

Explanations

references to health risks and related conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

iska

-0.16

lÄ±

-0.16

PIP

-0.15

uploaded

-0.15

meer

-0.14

tring

-0.14

angan

-0.14

egas

-0.14

egative

-0.14

POSITIVE LOGITS

iest

0.33

 factors

0.30

ier

0.30

iness

0.27

 Factors

0.25

 factor

0.24

ily

0.23

 posed

0.22

factor

0.20

 exposure

0.20

Activations Density 0.029%

references to health risks and related conditions

No Comments

No Known Activations