INDEX

Explanations

references to military training and qualifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

etter

-0.16

abar

-0.15

anni

-0.15

 Squadron

-0.14

rides

-0.14

ucker

-0.14

ÐµÑĢÐ°Ð¿

-0.14

Ãºsqueda

-0.13

ponent

-0.13

_lead

-0.13

POSITIVE LOGITS

sold

0.56

 sold

0.54

 Sold

0.48

Sold

0.47

 SOLD

0.46

 soldiers

0.43

_sold

0.39

 soldier

0.39

 ÑģÐ¾Ð»

0.35

sol

0.34

Activations Density 0.188%

references to military training and qualifications

No Comments

No Known Activations