INDEX

Explanations

terms related to healthcare and professional roles, particularly in nursing and midwifery

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ifa

-0.16

zi

-0.16

Ì£

-0.15

utz

-0.15

 perman

-0.15

èĴ

-0.15

rna

-0.14

alaria

-0.14

.prompt

-0.14

 permanent

-0.14

POSITIVE LOGITS

 stained

0.15

ently

0.15

ause

0.15

ć

0.15

ertino

0.14

anus

0.14

AUTH

0.14

ÐµÑĢÑĪ

0.14

igkeit

0.14

recogn

0.14

Activations Density 0.034%

terms related to healthcare and professional roles, particularly in nursing and midwifery

No Comments

No Known Activations