INDEX

Explanations

terms related to medical technology and diagnostics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

baum

-0.15

abile

-0.15

adow

-0.15

olean

-0.15

apiro

-0.14

ieren

-0.14

errated

-0.14

stanov

-0.14

rol

-0.13

 Bucket

-0.13

POSITIVE LOGITS

aced

0.16

umar

0.15

0.14

å¼Ħ

0.14

RECT

0.14

ombine

0.14

 Hayes

0.14

-found

0.13

aad

0.13

 Kong

0.13

Activations Density 0.047%

terms related to medical technology and diagnostics

No Comments

No Known Activations