INDEX

Explanations

references to military weaponry and systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

hsi

-0.15

 frauen

-0.14

çĪµ

-0.14

Î¿ÏħÎ»

-0.14

à¸£à¸ĩ

-0.14

gs

-0.14

 ÑĢÑĥÐº

-0.14

licht

-0.14

appings

-0.13

ÑĩÐ°ÑĤ

-0.13

POSITIVE LOGITS

 launch

0.20

 missile

0.20

 launches

0.19

 Missile

0.19

 fired

0.18

 launcher

0.17

ocket

0.17

-launch

0.17

 missiles

0.17

 launched

0.16

Activations Density 0.028%

references to military weaponry and systems

No Comments

No Known Activations