INDEX

Explanations

strategic language related to military operations and cyber defense

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

-0.15

å·¡

-0.15

rej

-0.14

icit

-0.14

icha

-0.14

 cannons

-0.14

DRAM

-0.13

 doomed

-0.13

_probe

-0.13

ENER

-0.13

POSITIVE LOGITS

 Doctrine

0.17

 doctrine

0.16

 Overwatch

0.16

 doctr

0.15

doctrine

0.15

-task

0.15

 Swinger

0.15

ensively

0.15

 assets

0.15

 Intelligence

0.14

Activations Density 0.226%

strategic language related to military operations and cyber defense

No Comments

No Known Activations