INDEX

Explanations

terms related to health and medical testing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

afs

-0.16

-0.15

ä¸ģ

-0.15

cken

-0.15

_frm

-0.14

omal

-0.14

thic

-0.14

oder

-0.14

oto

-0.14

sur

-0.14

POSITIVE LOGITS

ahlen

0.18

 Barker

0.17

 tuning

0.17

Ro

0.17

elsen

0.16

erer

0.15

 acomp

0.15

-ro

0.15

Parallel

0.15

ÑĢÐ¾

0.15

Activations Density 0.028%

terms related to health and medical testing

No Comments

No Known Activations