INDEX

Explanations

occurrences of requests, applications, and mentions related to choices or options

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ÅĦst

-0.18

cente

-0.17

kiye

-0.17

ramid

-0.14

.sdk

-0.14

libs

-0.14

ÄĽnÃŃ

-0.14

maal

-0.14

ToLeft

-0.14

ogan

-0.14

POSITIVE LOGITS

umpt

0.16

-fetch

0.15

utt

0.14

urban

0.14

onec

0.14

oice

0.14

UGHT

0.14

Jam

0.13

 introduction

0.13

 materials

0.13

Activations Density 0.169%

occurrences of requests, applications, and mentions related to choices or options

No Comments

No Known Activations