INDEX

Explanations

words associated with health-related conditions and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Sh

-0.34

SH

-0.29

/Sh

-0.25

¬¸

-0.24

×

-0.24

.Sh

-0.23

(S

-0.22

-Sh

-0.22

-S

-0.20

_Sh

-0.20

POSITIVE LOGITS

 shelter

0.38

 shore

0.38

 shores

0.35

 shelters

0.30

ãģĹãģĭ

0.29

 shoreline

0.28

ish

0.28

·

0.28

 Shelter

0.28

ä»Ģ

0.27

Activations Density 0.025%

words associated with health-related conditions and their implications

No Comments

No Known Activations