INDEX

Explanations

references to naval organizations and historical naval activities

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

 Demp

-0.16

 Sergeant

-0.14

 Frontier

-0.14

 Regiment

-0.14

 Army

-0.14

à¤¦à¤®

-0.14

olic

-0.14

_dl

-0.13

Sgt

-0.13

 civilian

-0.13

POSITIVE LOGITS

 flagship

0.22

 Dread

0.21

 fleet

0.20

 fleets

0.19

 Nelson

0.19

 cruis

0.18

adm

0.18

 Rodney

0.18

 Hood

0.17

 dread

0.17

Activations Density 0.035%

references to naval organizations and historical naval activities

No Comments

No Known Activations