INDEX

Explanations

references to 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 @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 Coca

-0.14

gere

-0.14

 Genel

-0.14

 Toshiba

-0.14

 Panasonic

-0.14

zend

-0.14

 Pepsi

-0.13

WithValue

-0.13

 Ð¿Ð¾Ð¼

-0.13

inee

-0.13

POSITIVE LOGITS

 sedan

0.21

car

0.20

 cars

0.18

 hatch

0.18

sport

0.18

otec

0.18

 Coupe

0.18

Sed

0.17

swagen

0.17

sed

0.17

Activations Density 0.085%

references to specific car models and their characteristics

No Comments

No Known Activations