INDEX

Explanations

mathematical terms and concepts related to geometry and topology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ãĥ³ãĥĸ

-0.14

 hier

-0.14

oran

-0.14

urban

-0.14

Ø§Ø¨Ø¹

-0.14

plier

-0.13

 presently

-0.13

ÛĮØ§

-0.13

 Boot

-0.13

ãĥ¼ãĥĲ

-0.13

POSITIVE LOGITS

 intuition

0.15

Mappings

0.15

icies

0.15

Å¾el

0.14

 (*((

0.14

ollo

0.14

proof

0.14

 incentiv

0.14

ãĥ¬ãĥ¼

0.14

hart

0.14

Activations Density 0.261%

mathematical terms and concepts related to geometry and topology

No Comments

No Known Activations