INDEX

Explanations

references to military honors and decorations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Ä±sÄ±t

-0.15

#__

-0.15

uve

-0.14

 Humph

-0.14

lei

-0.14

lements

-0.14

 Shields

-0.14

roker

-0.14

umph

-0.14

å¢

-0.14

POSITIVE LOGITS

itar

0.17

DialogContent

0.16

rray

0.14

prit

0.14

 Hart

0.14

ukan

0.14

 Clips

0.14

sak

0.14

iasi

0.14

ynes

0.14

Activations Density 0.035%

references to military honors and decorations

No Comments

No Known Activations