INDEX

Explanations

technical terms and concepts related to programming and software development

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

SupportedContent

-0.16

adoo

-0.15

åĢī

-0.15

Mov

-0.15

 redundancy

-0.14

leshooting

-0.14

Ð¡Ð¡Ðł

-0.14

æĵ¦

-0.14

 paramet

-0.14

éº»

-0.14

POSITIVE LOGITS

 processing

0.17

æ´¾

0.17

 ExecutionContext

0.16

processing

0.15

UserCode

0.15

jer

0.14

uges

0.14

atz

0.14

.run

0.14

 subur

0.14

Activations Density 0.065%

technical terms and concepts related to programming and software development

No Comments

No Known Activations