INDEX

Explanations

terms and phrases related to medical concepts and terminology

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

erie

-0.20

tz

-0.18

eries

-0.17

lette

-0.16

erg

-0.16

enheim

-0.16

ors

-0.16

hol

-0.15

ittel

-0.15

REATE

-0.15

POSITIVE LOGITS

ting

0.27

ernal

0.19

ernity

0.19

ismus

0.18

à¸¡

0.18

istic

0.17

apult

0.17

ucson

0.17

amer

0.16

rices

0.16

Activations Density 0.354%

terms and phrases related to medical concepts and terminology

No Comments

No Known Activations