INDEX

Explanations

technical terms and concepts related to GPS and location data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

boom

-0.17

ocking

-0.16

ohan

-0.16

ãģ¤ãģ¶

-0.16

 Graham

-0.14

áºł

-0.14

ohana

-0.14

PointSize

-0.14

SORT

-0.14

zac

-0.14

POSITIVE LOGITS

acent

0.18

/Area

0.16

 cent

0.15

 stabilized

0.15

å¾ģ

0.15

amental

0.14

 Uploaded

0.13

 stable

0.13

gem

0.13

agh

0.13

Activations Density 0.056%

technical terms and concepts related to GPS and location data

No Comments

No Known Activations