INDEX

Explanations

terms related to law enforcement and policing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

-0.16

äºľ

-0.15

odia

-0.15

Ã¡lu

-0.15

eds

-0.15

ncia

-0.15

xB

-0.14

ieren

-0.14

ìłĪ

-0.14

Ã¡tu

-0.14

POSITIVE LOGITS

owy

0.26

ovÃ½

0.22

owego

0.22

owych

0.21

ìłģìĿ¸

0.20

owe

0.20

owej

0.20

liche

0.20

nÃŃ

0.19

elijke

0.18

Activations Density 0.081%

terms related to law enforcement and policing

No Comments

No Known Activations