INDEX

Explanations

references to previous sections or propositions in mathematical texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ime

-0.15

á»ĭch

-0.14

aque

-0.14

neau

-0.14

ÃŃrk

-0.14

nga

-0.14

Ã²ng

-0.14

isty

-0.14

åħ·

-0.14

Ø·Ø§Ø±

-0.14

POSITIVE LOGITS

 defaultCenter

0.16

Î¾Î¹

0.15

 Provincial

0.14

aspers

0.14

 compounded

0.14

acom

0.14

ubb

0.13

à¤¬à¤²

0.13

 voks

0.13

 curs

0.13

Activations Density 0.021%

references to previous sections or propositions in mathematical texts

No Comments

No Known Activations