INDEX

Explanations

technical terminology related to network communication and security

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

odom

-0.19

 Horse

-0.17

 horse

-0.16

 horses

-0.16

rove

-0.16

CharacterSet

-0.16

RAINT

-0.15

Disk

-0.14

olid

-0.14

RLF

-0.14

POSITIVE LOGITS

 Flow

0.26

 flow

0.25

 packet

0.25

Flow

0.24

 packets

0.24

.Flow

0.24

 flows

0.23

_flow

0.23

FLOW

0.23

mac

0.23

Activations Density 0.023%

technical terminology related to network communication and security

No Comments

No Known Activations