INDEX

Explanations

terms and phrases related to medical conditions, particularly emphasizing their symptoms and effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

achel

-0.15

æ¬ł

-0.14

 Collision

-0.14

ÐµÐ½Ñı

-0.14

 suffers

-0.14

 sanitize

-0.14

sanitize

-0.14

erguson

-0.14

ulong

-0.13

amilia

-0.13

POSITIVE LOGITS

 affect

0.23

 occurs

0.23

 occur

0.22

 manifest

0.21

occ

0.21

 develops

0.21

 affects

0.20

 develop

0.20

manifest

0.20

 afect

0.19

Activations Density 0.124%

terms and phrases related to medical conditions, particularly emphasizing their symptoms and effects

No Comments

No Known Activations