INDEX

Explanations

terms related to newborn health assessments and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 pregnant

-0.20

 Pregn

-0.19

preg

-0.19

 Pregnancy

-0.17

 pregnancy

-0.17

vetica

-0.16

 menstr

-0.16

usercontent

-0.15

 preg

-0.15

 menstrual

-0.15

POSITIVE LOGITS

 neon

0.39

 Neon

0.38

umb

0.28

 newborn

0.28

 cord

0.27

NIC

0.27

 born

0.26

ja

0.25

 infants

0.25

cord

0.24

Activations Density 0.027%

terms related to newborn health assessments and evaluations

No Comments

No Known Activations