INDEX

Explanations

key details and specific numbers related to costs, quantities, or prices associated with various products or services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ictim

-0.16

rub

-0.16

orex

-0.15

bard

-0.15

 Werk

-0.14

anzi

-0.14

DAQ

-0.14

oley

-0.14

_RCC

-0.14

tring

-0.13

POSITIVE LOGITS

 cost

0.33

cost

0.30

 costing

0.29

 weighs

0.27

 Cost

0.27

 costa

0.26

Cost

0.25

 clocks

0.24

 costs

0.24

_cost

0.24

Activations Density 0.168%

key details and specific numbers related to costs, quantities, or prices associated with various products or services

No Comments

No Known Activations