INDEX

Explanations

technical terms related to programming and job processing

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

InterfaceOrientation

-0.15

adc

-0.15

chie

-0.15

aukee

-0.14

InitStruct

-0.13

Ã±a

-0.13

ETY

-0.13

 truck

-0.13

MU

-0.13

 Blitz

-0.13

POSITIVE LOGITS

 subscription

0.33

 subscribe

0.32

subscribe

0.32

 Subscriber

0.32

 Subscription

0.31

 subscriber

0.31

subscription

0.31

Subscription

0.30

Subscribe

0.29

.subscribe

0.28

Activations Density 0.012%

technical terms related to programming and job processing

No Comments

No Known Activations