INDEX

Explanations

mathematical notations and symbols used in formal proofs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

itz

-0.17

er

-0.17

adan

-0.16

herits

-0.15

peg

-0.15

liÄŁinde

-0.15

alty

-0.14

ER

-0.14

ocl

-0.14

ered

-0.13

POSITIVE LOGITS

ucci

0.18

0.17

ATUS

0.16

tun

0.16

ObjectContext

0.15

 commande

0.15

0.14

xious

0.14

Ø²ÙĬØ©

0.14

Activations Density 0.033%

mathematical notations and symbols used in formal proofs

No Comments

No Known Activations