INDEX

Explanations

key terms and identifiers in software documentation and programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

izik

-0.17

inas

-0.15

oves

-0.14

ÏģÎ¹Î¬

-0.14

 Mits

-0.14

ovÃ¡n

-0.14

Ä±rÄ±

-0.14

 Centers

-0.14

ER

-0.14

elp

-0.13

POSITIVE LOGITS

éĬ

0.17

rost

0.16

0.15

orate

0.15

istencia

0.14

 Karlov

0.14

cco

0.14

 Feinstein

0.14

 Amar

0.14

Activations Density 0.001%

key terms and identifiers in software documentation and programming contexts

No Comments

No Known Activations