INDEX

Explanations

mathematical symbols and notations related to convergence in proving mathematical theorems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

 SqlDbType

-0.16

ReturnValue

-0.16

eya

-0.15

oret

-0.15

ÙĬØ¯Ø§

-0.15

esters

-0.14

à¸Ĩ

-0.14

opp

-0.14

rics

-0.14

luet

-0.14

POSITIVE LOGITS

iff

0.32

 implies

0.30

 implication

0.27

 impl

0.26

 imply

0.25

 holds

0.25

impl

0.24

 Impl

0.24

_impl

0.24

IFF

0.22

Activations Density 0.128%

mathematical symbols and notations related to convergence in proving mathematical theorems

No Comments

No Known Activations