INDEX

Explanations

mentions of police and law enforcement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 police

-0.27

 Police

-0.24

Police

-0.21

 policing

-0.21

 policemen

-0.20

ship

-0.19

shit

-0.17

èŃ¦å¯Ł

-0.17

 policeman

-0.17

rog

-0.16

POSITIVE LOGITS

 officers

0.27

 officer

0.25

 Officers

0.21

 station

0.20

 brutality

0.20

able

0.20

 stations

0.20

 Brut

0.19

 department

0.19

 chief

0.19

Activations Density 0.033%

mentions of police and law enforcement

No Comments

No Known Activations