INDEX

Explanations

references to discounts, deals, and promotions related to purchases

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

 Through

-0.32

Through

-0.31

-through

-0.24

_through

-0.24

Between

-0.21

through

-0.21

although

-0.21

Among

-0.20

 Among

-0.20

 THROUGH

-0.20

POSITIVE LOGITS

 right

0.33

 abroad

0.32

 around

0.30

 anytime

0.30

 over

0.29

 anywhere

0.28

on

0.28

 today

0.28

 below

0.28

 away

0.27

Activations Density 0.115%

references to discounts, deals, and promotions related to purchases

No Comments

No Known Activations