INDEX

Explanations

mentions of political conflict or military actions related to Israel and Iran

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

onder

-0.16

ordum

-0.14

Ð´Ð¸Ð½

-0.13

<?,

-0.13

vation

-0.13

 Hari

-0.13

bootstrap

-0.13

ihar

-0.13

POSITIVE LOGITS

 plots

0.25

 colonial

0.24

plots

0.21

 Juda

0.20

 plot

0.20

 Zion

0.20

 schemes

0.20

 plotting

0.20

 provocative

0.19

 Colonial

0.18

Activations Density 0.064%

mentions of political conflict or military actions related to Israel and Iran

No Comments

No Known Activations