INDEX

Explanations

vocabulary related to military service and training

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 civilian

-0.21

ADDE

-0.18

ucker

-0.17

 haut

-0.17

Ñī

-0.16

 Squadron

-0.16

ï¾ī

-0.16

issan

-0.15

 Milit

-0.15

Ãºsqueda

-0.15

POSITIVE LOGITS

 sold

0.39

sold

0.35

tro

0.33

 Sold

0.31

 SOLD

0.29

Sold

0.29

sol

0.29

 personnel

0.27

men

0.26

 solid

0.26

Activations Density 0.106%

vocabulary related to military service and training

No Comments

No Known Activations