INDEX

Explanations

instances of code and programming-related terms within the text

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

ekil

-0.17

eyse

-0.16

åĪ°åºķ

-0.16

Î²Î¬Î»

-0.15

pled

-0.15

bei

-0.14

IDD

-0.14

bon

-0.14

adius

-0.14

ourcem

-0.14

POSITIVE LOGITS

 Marketable

0.17

uli

0.16

anlar

0.15

 Observatory

0.14

cur

0.14

arch

0.13

 Bulletin

0.13

 Offering

0.13

èħ

0.13

Activations Density 0.014%

instances of code and programming-related terms within the text

No Comments

No Known Activations