INDEX

Explanations

concepts related to algorithms and network protocols

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 sunday

-0.14

 ipad

-0.14

diy

-0.14

unix

-0.14

 african

-0.14

 china

-0.14

 raspberry

-0.13

 samsung

-0.13

dvd

-0.13

 iphone

-0.13

POSITIVE LOGITS

 requests

0.32

 calls

0.26

 incoming

0.25

 queries

0.24

 connections

0.23

 outgoing

0.23

 accesses

0.23

 inbound

0.23

 traffic

0.22

 communications

0.22

Activations Density 0.142%

concepts related to algorithms and network protocols

No Comments

No Known Activations