INDEX

Explanations

references to trade-related terms and discussions about tariffs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Å¡en

-0.15

ropp

-0.14

Ð¸ÑĪ

-0.14

æ¨¹

-0.14

.Pixel

-0.14

Intl

-0.14

 Accountability

-0.14

ÏħÎ³

-0.14

ahi

-0.13

LOPT

-0.13

POSITIVE LOGITS

 prefer

0.34

 duty

0.32

 preferences

0.31

 preference

0.30

 duties

0.28

 Prefer

0.27

 Preferences

0.27

 Duty

0.26

 Preference

0.26

 tariff

0.25

Activations Density 0.023%

references to trade-related terms and discussions about tariffs

No Comments

No Known Activations