INDEX

Explanations

code elements related to data processing and configuration settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 ................................................................

-0.18

âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦

-0.17

................................................................

-0.16

 ................................

-0.15

ulty

-0.15

astery

-0.14

avin

-0.14

 __________________________________

-0.14

 telecommunications

-0.14

POSITIVE LOGITS

 &↵

0.29

 \↵

0.29

\↵

0.24

 ${↵

0.21

,\↵

0.21

 "\↵

0.20

ãĢģ↵

0.20

(↵

0.20

 acknow

0.18

 misunder

0.17

Activations Density 1.945%

code elements related to data processing and configuration settings

No Comments

No Known Activations