INDEX

Explanations

mentions of specific vehicle brands and models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

expo

-0.17

á»¥c

-0.16

apolis

-0.15

stdarg

-0.15

Ý

-0.15

senal

-0.15

ething

-0.14

 Damascus

-0.14

emon

-0.14

/Dk

-0.14

POSITIVE LOGITS

 Jaguar

0.29

 Jaguars

0.23

XK

0.21

 Land

0.19

 Birmingham

0.19

jag

0.19

 Ingen

0.17

 Covent

0.16

 Gujar

0.16

 Kapoor

0.16

Activations Density 0.006%

mentions of specific vehicle brands and models

No Comments

No Known Activations