INDEX

Explanations

terms related to defense and military topics

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

Cru

-0.16

 defensive

-0.15

idunt

-0.15

ottes

-0.15

 Defence

-0.15

 defended

-0.15

 defensively

-0.15

 defence

-0.14

formats

-0.14

ridge

-0.14

POSITIVE LOGITS

less

0.28

lessness

0.26

 against

0.25

 mechanism

0.24

 contractor

0.24

 posture

0.23

 mechanisms

0.23

 contractors

0.22

 spending

0.21

 Against

0.21

Activations Density 0.025%

terms related to defense and military topics

No Comments

No Known Activations

terms related to defense and military topics

No Comments

No Known Activations