INDEX

Explanations

references to military operations and logistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ullan

-0.14

 Affero

-0.14

ARGIN

-0.14

 QTableWidgetItem

-0.14

.presentation

-0.14

occup

-0.14

ç°

-0.13

idel

-0.13

ichen

-0.13

olla

-0.13

POSITIVE LOGITS

 exercises

0.22

 participants

0.21

 Joint

0.20

 participation

0.20

æ¼Ķ

0.19

Joint

0.19

 participant

0.18

 Exercise

0.18

 exercise

0.18

 participating

0.18

Activations Density 0.014%

references to military operations and logistics

No Comments

No Known Activations