INDEX

Explanations

terms related to automotive history and innovations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

 Madden

-0.18

 Demp

-0.17

omi

-0.15

.bio

-0.15

Nes

-0.15

Eis

-0.14

è»¢

-0.14

_GC

-0.14

Mig

-0.14

 repe

-0.14

POSITIVE LOGITS

 autom

0.22

PSA

0.22

 Autom

0.20

 Motors

0.19

 Passenger

0.19

Autom

0.18

auto

0.18

 ÎĮÎ¼Î¹Î»Î¿ÏĤ

0.18

 Automotive

0.18

 Chrysler

0.18

Activations Density 0.047%

terms related to automotive history and innovations

No Comments

No Known Activations