INDEX

Explanations

references to specific car models and performance characteristics

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

chalk

-0.17

 wholesalers

-0.17

trieve

-0.15

 ìĭ

-0.15

EEP

-0.14

ëĳ¥

-0.14

ìĽĮ

-0.14

aura

-0.14

 Provid

-0.14

onn

-0.13

POSITIVE LOGITS

 sports

0.24

 Ferrari

0.20

 convertible

0.19

 exotic

0.19

Zag

0.19

 coupe

0.19

 Sports

0.18

Cay

0.18

 McLaren

0.18

GT

0.18

Activations Density 0.098%

references to specific car models and performance characteristics

No Comments

No Known Activations