INDEX

Explanations

terms related to diesel engines and fuel systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

car

-0.21

 cars

-0.17

ermann

-0.15

 Automobile

-0.15

/car

-0.15

(car

-0.15

ucher

-0.15

aptic

-0.14

legacy

-0.14

outh

-0.14

POSITIVE LOGITS

 Tier

0.21

Cum

0.19

Cum

0.19

Tier

0.17

cab

0.17

 gens

0.17

Cab

0.15

cum

0.15

Cab

0.15

Yan

0.15

Activations Density 0.038%

terms related to diesel engines and fuel systems

No Comments

No Known Activations