INDEX

Explanations

terms related to vehicles and automotive topics

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

ped

-0.17

holm

-0.16

iyat

-0.16

 Contents

-0.15

emm

-0.15

olet

-0.15

Ð¼ÐµÑĢÐ¸Ðº

-0.15

-corner

-0.15

/qu

-0.14

ë¹ĦìĬ¤

-0.14

POSITIVE LOGITS

ives

0.17

ting

0.16

ived

0.16

agma

0.15

unidad

0.15

ets

0.14

luk

0.14

tingham

0.14

ands

0.14

inky

0.14

Activations Density 0.011%

terms related to vehicles and automotive topics

No Comments

No Known Activations