INDEX

Explanations

references to data storage and organizational methods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 Breed

-0.16

olson

-0.15

Nob

-0.15

-0.14

allas

-0.14

-0.13

 Baths

-0.13

POSITIVE LOGITS

 storage

0.17

opi

0.16

age

0.15

 Linear

0.15

Å¡t

0.15

 Storage

0.15

 storing

0.15

amt

0.14

é¡

0.14

Linear

0.14

Activations Density 0.136%

references to data storage and organizational methods

No Comments

No Known Activations