INDEX

Explanations

phrases related to product descriptions and specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 vent

-0.14

lech

-0.13

orama

-0.13

 sucking

-0.13

à¹Ģà¸Ł

-0.13

ILA

-0.13

 Poll

-0.13

 selectively

-0.13

Sar

-0.13

ÑĢÑİ

-0.13

POSITIVE LOGITS

 formula

0.39

formula

0.35

 formulas

0.32

 recipe

0.32

 formulation

0.31

 blend

0.30

 reform

0.30

 formul

0.29

Formula

0.29

 ingredient

0.28

Activations Density 0.152%

phrases related to product descriptions and specifications

No Comments

No Known Activations