INDEX

Explanations

terms related to health and healthcare professions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ewire

-0.16

NSE

-0.15

ectl

-0.14

æµ¦

-0.14

obile

-0.14

rais

-0.14

ISCO

-0.13

WARDS

-0.13

sek

-0.13

 mbox

-0.13

POSITIVE LOGITS

chter

0.17

acles

0.15

Isl

0.14

Ã³Å¼

0.14

anth

0.14

illance

0.14

 Preview

0.14

 Wheels

0.14

ifice

0.14

 modelAndView

0.14

Activations Density 0.399%

terms related to health and healthcare professions

No Comments

No Known Activations