INDEX

Explanations

details about physical dimensions and specifications of objects or devices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Interpolator

-0.13

zcze

-0.13

è°

-0.13

eyin

-0.13

SourceType

-0.13

 dlouhodob

-0.12

 almak

-0.12

è¬

-0.12

 movers

-0.12

 Ø¢Ùħ

-0.12

POSITIVE LOGITS

 height

0.53

 width

0.52

 length

0.48

 diameter

0.44

 depth

0.41

 dimensions

0.40

 thickness

0.40

 breadth

0.36

 size

0.35

 dimension

0.35

Activations Density 0.171%

details about physical dimensions and specifications of objects or devices

No Comments

No Known Activations