INDEX

Explanations

specific automotive and vehicle-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

usto

-0.17

 åĨĨ

-0.16

 Ferrari

-0.14

enty

-0.14

lice

-0.14

DMA

-0.14

 charger

-0.13

erto

-0.13

vice

-0.13

POSITIVE LOGITS

ãĤ¤ãĥī

0.16

Ð¾ÑĩÐµÐº

0.15

äº®

0.14

Ø±ÛĮÙģ

0.14

 sodom

0.14

ManagerInterface

0.13

Ø±ØŃ

0.13

grese

0.13

_EVT

0.13

']!='

0.13

Activations Density 0.094%

specific automotive and vehicle-related terms

No Comments

No Known Activations