INDEX

Explanations

key information related to product pricing 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

orex

-0.15

adero

-0.15

ilon

-0.14

oley

-0.14

igne

-0.14

cx

-0.14

toi

-0.13

Ø¹Ø§ÙĨ

-0.13

Builder

-0.13

 Sergeant

-0.13

POSITIVE LOGITS

 cost

0.42

 costs

0.41

cost

0.39

 costing

0.38

 Costs

0.36

 prices

0.35

 price

0.35

 priced

0.35

price

0.33

 Cost

0.33

Activations Density 0.163%

key information related to product pricing and specifications

No Comments

No Known Activations