INDEX

Explanations

numerical data related to medical systems 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 @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uple

-0.15

MIS

-0.14

enment

-0.14

 Polic

-0.14

amo

-0.14

 cord

-0.13

Sob

-0.13

cai

-0.13

pai

-0.13

 neither

-0.13

POSITIVE LOGITS

lesen

0.15

igel

0.14

YNC

0.14

onio

0.14

.gf

0.14

aab

0.14

à¸£à¸ģ

0.14

ÑĢÐµÑģÑĤ

0.14

ãĤ¦ãĥ³

0.13

ÑĢÑĥÐºÑĤ

0.13

Activations Density 0.045%

numerical data related to medical systems and diagnostics

No Comments

No Known Activations