INDEX

Explanations

references to military medals and honors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ANDOM

-0.16

atham

-0.15

kee

-0.15

_feed

-0.15

Ã´n

-0.14

Ø§Ø³Ø§ÙĨ

-0.14

 Transparent

-0.14

viar

-0.14

 Chanel

-0.14

cura

-0.14

POSITIVE LOGITS

 earned

0.20

icode

0.20

 credits

0.18

 credit

0.15

 earn

0.15

 experience

0.15

earned

0.15

 exposure

0.15

 holder

0.15

 combat

0.14

Activations Density 0.093%

references to military medals and honors

No Comments

No Known Activations