INDEX

Explanations

references to police technology and operational challenges

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

asley

-0.16

	DECLARE

-0.14

 armies

-0.14

VERR

-0.13

 Shuttle

-0.13

çĻ»

-0.13

ssi

-0.13

 Executors

-0.13

oso

-0.13

loon

-0.13

POSITIVE LOGITS

 officer

0.44

 officers

0.42

 Officer

0.38

 police

0.37

 Officers

0.36

 department

0.34

 Police

0.34

 cops

0.33

 patrol

0.32

Police

0.30

Activations Density 0.322%

references to police technology and operational challenges

No Comments

No Known Activations