INDEX

Explanations

references to police activity and emergency response situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

afil

-0.17

ãĥªãĥ¼ãĤº

-0.15

ikat

-0.15

ourg

-0.15

mÃŃt

-0.14

ernaut

-0.14

laus

-0.14

 Sher

-0.14

AAF

-0.14

reeze

-0.14

POSITIVE LOGITS

 dispatched

0.28

 dispatch

0.25

 call

0.23

 attendance

0.23

 responding

0.23

 response

0.23

 Dispatch

0.22

 respond

0.22

 Attendance

0.22

 responded

0.21

Activations Density 0.058%

references to police activity and emergency response situations

No Comments

No Known Activations