INDEX

Explanations

technical terms and concepts related to programming, databases, and development

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

apon

-0.16

pons

-0.15

lech

-0.14

APON

-0.14

ÐĴÑĤ

-0.14

hek

-0.14

endo

-0.14

wers

-0.14

-0.13

POSITIVE LOGITS

vanished

0.19

chten

0.18

ãĥ¥ãĥ¼

0.17

dur

0.17

unma

0.16

ensburg

0.15

asp

0.14

 Levine

0.14

 alternative

0.14

Ã¼ven

0.14

Activations Density 0.002%

technical terms and concepts related to programming, databases, and development

No Comments

No Known Activations