INDEX

Explanations

references to computational models and simulations relating to network flow dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

upe

-0.15

Zem

-0.15

GuidId

-0.14

.Invariant

-0.13

Circular

-0.13

etimes

-0.13

/bind

-0.13

_PEER

-0.13

unch

-0.13

_nsec

-0.13

POSITIVE LOGITS

 mesh

0.30

 cell

0.29

 cells

0.29

 grid

0.28

 Cell

0.28

 Mesh

0.27

-cell

0.27

mesh

0.26

-grid

0.26

 Cells

0.25

Activations Density 0.050%

references to computational models and simulations relating to network flow dynamics

No Comments

No Known Activations