INDEX

Explanations

references to lotteries and rewards associated with them

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

 Rating

-0.18

 rating

-0.17

 Ratings

-0.16

äº¤æĺĵ

-0.15

rating

-0.15

Rating

-0.15

 Mour

-0.15

emoc

-0.14

eneric

-0.14

 ratings

-0.14

POSITIVE LOGITS

 ticket

0.22

 drawn

0.21

 jackpot

0.20

 tickets

0.20

 lottery

0.20

rollo

0.20

 draw

0.20

 Mega

0.19

 drawing

0.19

 Draw

0.19

Activations Density 0.010%

references to lotteries and rewards associated with them

No Comments

No Known Activations