INDEX

Explanations

phrases related to conflict and rivalry

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

ekler

-0.16

idla

-0.16

entai

-0.15

orro

-0.15

Ð¾ÑıÑĤÐµÐ»ÑĮ

-0.15

oubted

-0.14

ÃĹ↵↵

-0.14

erli

-0.14

Ð»Ð¸Ð¶

-0.13

è¿ŀæİ¥

-0.13

POSITIVE LOGITS

 between

0.28

 tensions

0.23

 tension

0.23

between

0.23

 heated

0.22

tug

0.21

 Between

0.21

 tranh

0.21

 conflict

0.21

 conflicts

0.20

Activations Density 0.338%

phrases related to conflict and rivalry

No Comments

No Known Activations