INDEX

Explanations

components related to medical and forensic contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ãĥ¼ãĥŃ

-0.19

-in

-0.16

uiten

-0.14

-In

-0.14

acades

-0.14

 Gabri

-0.14

iaz

-0.13

æ¢¨

-0.13

 rect

-0.13

Mr

-0.13

POSITIVE LOGITS

åĳ½

0.15

brig

0.15

ehr

0.14

woord

0.14

ÐµÑĢÐ°Ð¿

0.14

REET

0.14

 porad

0.14

 ÑĥÐ»ÑĥÑĩ

0.14

 createState

0.14

Activations Density 0.016%

components related to medical and forensic contexts

No Comments

No Known Activations