INDEX

Explanations

references to English language education programs and institutions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Princip

-0.16

 Weiner

-0.16

 bilingual

-0.15

esity

-0.14

ivial

-0.14

Î¹Î½

-0.14

-0.13

è¥²

-0.13

mal

-0.13

esimal

-0.13

POSITIVE LOGITS

æŃĮ

0.17

loon

0.15

ModelProperty

0.15

ç¥

0.14

ä½³

0.14

Ã¡z

0.14

rys

0.13

aser

0.13

ears

0.13

OX

0.13

Activations Density 0.029%

references to English language education programs and institutions

No Comments

No Known Activations