INDEX

Explanations

technical terms and references related to scientific and medical topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

 TMPro

-0.16

anik

-0.15

ovalo

-0.15

ãģĺ

-0.15

ERSION

-0.14

CAPE

-0.14

 ÄĮer

-0.14

Bindable

-0.14

izon

-0.14

mpp

-0.14

POSITIVE LOGITS

egov

0.15

burn

0.15

fol

0.15

(s

0.14

rend

0.14

ime

0.14

asia

0.14

ì§Ŀ

0.14

 sama

0.14

Activations Density 0.536%

technical terms and references related to scientific and medical topics

No Comments

No Known Activations