INDEX

Explanations

negations and references to discrepancies in traditional practices of numerology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 vill

-0.15

ivia

-0.15

 Milli

-0.15

 Oliv

-0.14

ãĥ£

-0.14

amine

-0.14

 nonzero

-0.14

 playable

-0.14

 somew

-0.13

bian

-0.13

POSITIVE LOGITS

é¦

0.16

nyder

0.16

.dim

0.15

xo

0.15

LETTE

0.15

etsk

0.15

 less

0.14

 slightest

0.14

oned

0.14

 neither

0.14

Activations Density 0.148%

negations and references to discrepancies in traditional practices of numerology

No Comments

No Known Activations