INDEX

Explanations

terms related to fuel systems and performance specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ombok

-0.16

InView

-0.15

chner

-0.15

uye

-0.15

 studio

-0.14

 fibre

-0.14

 Conce

-0.14

uve

-0.14

 Ø¯Ùħ

-0.14

elsing

-0.14

POSITIVE LOGITS

oil

0.27

 fuel

0.24

Oil

0.24

Oil

0.24

fuel

0.24

æ²¹

0.23

 Fuel

0.20

 oils

0.20

 petroleum

0.20

oil

0.20

Activations Density 0.078%

terms related to fuel systems and performance specifications

No Comments

No Known Activations