INDEX

Explanations

technical terms and jargon related to software or programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

 coco

-0.16

/xml

-0.15

 Transparent

-0.15

Schedulers

-0.15

ÐºÑĸÐ½

-0.15

ELLOW

-0.14

azers

-0.14

rompt

-0.14

mps

-0.14

orian

-0.14

POSITIVE LOGITS

 metric

0.21

 metrics

0.21

 instrumentation

0.21

collector

0.21

 collector

0.20

 Instrument

0.20

 instrument

0.20

 Metric

0.20

 Collector

0.20

instrument

0.19

Activations Density 0.028%

technical terms and jargon related to software or programming

No Comments

No Known Activations