INDEX

Explanations

mentions of specific car models and their characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

adero

-0.15

CTYPE

-0.14

STER

-0.14

ymm

-0.14

Gil

-0.14

 alone

-0.13

ç¹ģ

-0.13

 exper

-0.13

à¸²à¸Ľ

-0.13

erse

-0.13

POSITIVE LOGITS

 cheap

0.42

cheap

0.40

Cheap

0.39

 inexpensive

0.39

 Cheap

0.38

 cheapest

0.34

 cheaper

0.33

 ráº»

0.31

 affordable

0.28

 cost

0.27

Activations Density 0.206%

mentions of specific car models and their characteristics

No Comments

No Known Activations