INDEX

Explanations

incidents involving police actions and confrontations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

oire

-0.17

urette

-0.16

@}

-0.16

RIA

-0.15

erin

-0.15

imo

-0.15

 Trab

-0.15

 Guards

-0.15

 guards

-0.14

 vá»ĩ

-0.14

POSITIVE LOGITS

 officers

0.21

 pursuit

0.20

TAS

0.19

tas

0.19

 officer

0.18

 Purs

0.18

 pursuits

0.17

 Officer

0.16

 appreh

0.16

 Officers

0.16

Activations Density 0.044%

incidents involving police actions and confrontations

No Comments

No Known Activations